{
  "$schema": "https://receiptaudit.com/benchmarks/schema.json",
  "suite": "receipt-audit",
  "title": "RA-Bench: receipt extraction, fake detection and duplicates",
  "preliminary": true,
  "disclosure": "We build Receipt Audit and we run this benchmark. Our engine is one of the targets, so read it as a vendor benchmark: the public split's cases, labels, every target's outputs and the code are open, every run is kept, and losses are listed first. To reproduce a number, run the command below with your own keys; to dispute one, email hello@godard.me.",
  "manifest": {
    "runId": "20261012T203648Z-44a89a",
    "suite": "receipt-audit",
    "suiteVersion": "0.1.0",
    "datasetHash": "d36eb9d9f3c39095eb98d466bc8d846364ba8c6f867bac21dbdb7e52762a15d8",
    "split": "public",
    "startedAt": "2026-10-12T20:36:48.316Z",
    "finishedAt": "2026-10-12T20:47:27.588Z",
    "gitSha": "533532d82afaf3d760175538264238fc09bcf17a",
    "reps": 1,
    "cases": 150,
    "targets": [
      {
        "id": "self",
        "label": "Receipt Audit (Gemini 3.8 Flash)",
        "kind": "self",
        "version": "google/gemini-3.8-flash+prompt.29e15e97ce93+git.533532d82afa",
        "config": {
          "engine": "ReceiptChecks (apps/receipt-check/lib/server/ReceiptChecks.ts), in process",
          "model": "google/gemini-3.8-flash",
          "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
          "reasoningEffort": "low",
          "structuredOutput": true,
          "modelTimeout": "90 seconds",
          "modelRetries": "2, on errors effect/ai marks retryable",
          "filePreparation": "upright, at most 3072 px and 3.75 MB (lib/receipts/model.ts)",
          "duplicateNetwork": "the production Convex functions on an in-memory backend, empty at the start of each repetition",
          "submitter": "one account per case (the case id)",
          "gitSha": "533532d82afaf3d760175538264238fc09bcf17a",
          "pricePerCheckUsd": 0.01633333333333333,
          "cost": "cost_per_check_usd is what a caller pays Receipt Audit per check: the list price of the smallest credit pack (credits-3k: $49 for 3,000 checks, $0.0163 per check). model_cost_per_check_usd (and each result's costUsd) is the engine's own model call: tokens × the AI Gateway list price on the price date."
        },
        "priceDate": "2026-10-12",
        "unsupportedTasks": []
      },
      {
        "id": "self-haiku",
        "label": "Receipt Audit (Claude Haiku 5.5)",
        "kind": "self",
        "version": "anthropic/claude-haiku-5.5+prompt.29e15e97ce93+git.533532d82afa",
        "config": {
          "engine": "ReceiptChecks (apps/receipt-check/lib/server/ReceiptChecks.ts), in process",
          "model": "anthropic/claude-haiku-5.5",
          "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
          "reasoningEffort": "low",
          "structuredOutput": true,
          "modelTimeout": "90 seconds",
          "modelRetries": "2, on errors effect/ai marks retryable",
          "filePreparation": "upright, at most 3072 px and 3.75 MB (lib/receipts/model.ts)",
          "duplicateNetwork": "the production Convex functions on an in-memory backend, empty at the start of each repetition",
          "submitter": "one account per case (the case id)",
          "gitSha": "533532d82afaf3d760175538264238fc09bcf17a",
          "pricePerCheckUsd": 0.01633333333333333,
          "cost": "cost_per_check_usd is what a caller pays Receipt Audit per check: the list price of the smallest credit pack (credits-3k: $49 for 3,000 checks, $0.0163 per check). model_cost_per_check_usd (and each result's costUsd) is the engine's own model call: tokens × the AI Gateway list price on the price date."
        },
        "priceDate": "2026-10-12",
        "unsupportedTasks": []
      },
      {
        "id": "diy:claude-haiku-5.5",
        "label": "Claude Haiku 5.5, plain prompt",
        "kind": "diy",
        "version": "claude-haiku-5-5@claude-code-cli+prompt.512dfb3893be+git.533532d82afa",
        "config": {
          "transport": "claude-code-cli",
          "endpoint": "http://127.0.0.1:8789/v1/messages (claude-local: one headless `claude -p` per call, no tools, no MCP, no settings, empty cwd)",
          "billing": "subscription",
          "cli": "claude 2.1.296",
          "thinking": "Claude Code default (adaptive; can't be fully disabled via the CLI)",
          "ignored": [
            "max_tokens"
          ],
          "costUsd": "API-equivalent: the reported tokens × the AI Gateway list price, i.e. what the check costs when called through the API",
          "usage": "as the CLI reports it, including Claude Code's own cached system prompt (about 3,500 tokens, mostly cache reads); inputTokens counts uncached, cache-read and cache-write tokens",
          "model": "claude-haiku-5-5",
          "max_tokens": 4096,
          "message": "one user turn: the file (image block, or document block for a PDF), then the prompt",
          "rateLimits": "HTTP 429 (a subscription limit on claude-local) is retried with backoff like a transport error",
          "prompt": "apps/receipt-check/bench/prompt.ts (DIY_PLAIN_PROMPT)",
          "promptSha256": "512dfb3893be5aa7f89ff7be2259d8f9c94c948fe8b2d6e3dca9bc6f5889bc37",
          "gitSha": "533532d82afaf3d760175538264238fc09bcf17a",
          "cost": "cost_per_check_usd and model_cost_per_check_usd are both the API-equivalent token cost: tokens × the AI Gateway list price on the price date"
        },
        "priceDate": "2026-10-12",
        "unsupportedTasks": [
          "checks",
          "duplicates"
        ]
      },
      {
        "id": "diy:gemini-3.8-flash",
        "label": "Gemini 3.8 Flash, plain prompt",
        "kind": "diy",
        "version": "google/gemini-3.8-flash+prompt.512dfb3893be+git.533532d82afa",
        "config": {
          "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions (Vercel AI Gateway, OpenAI-compatible)",
          "model": "google/gemini-3.8-flash",
          "max_tokens": "not set (provider default)",
          "reasoning": "not set (provider default)",
          "temperature": "not set (provider default)",
          "message": "one user turn: the file (image_url part, or a file part for a PDF), then the prompt",
          "prompt": "apps/receipt-check/bench/prompt.ts (DIY_PLAIN_PROMPT)",
          "promptSha256": "512dfb3893be5aa7f89ff7be2259d8f9c94c948fe8b2d6e3dca9bc6f5889bc37",
          "gitSha": "533532d82afaf3d760175538264238fc09bcf17a",
          "cost": "cost_per_check_usd and model_cost_per_check_usd are both the API-equivalent token cost: tokens × the AI Gateway list price on the price date"
        },
        "priceDate": "2026-10-12",
        "unsupportedTasks": [
          "checks",
          "duplicates"
        ]
      }
    ]
  },
  "metrics": [
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "all",
      "target": "self",
      "value": 1,
      "lo": 0.9213484012671117,
      "hi": 1,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "all",
      "target": "self",
      "value": 1,
      "lo": 0.9123783988027135,
      "hi": 1,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "all",
      "target": "self",
      "value": 1,
      "lo": 0.9229264369144198,
      "hi": 1,
      "n": 46,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "all",
      "target": "self",
      "value": 0.9655172413793104,
      "lo": 0.9146804594445852,
      "hi": 0.9865101724350616,
      "n": 116,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "all",
      "target": "self",
      "value": 0.9666666666666667,
      "lo": 0.917419662440894,
      "hi": 0.9869624489016494,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "all",
      "target": "self",
      "value": 0.95,
      "lo": 0.8951971146376326,
      "hi": 0.9768856355855343,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "all",
      "target": "self",
      "value": 1,
      "lo": 0.8620237953250198,
      "hi": 1,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "all",
      "target": "self",
      "value": 0.95,
      "lo": 0.8951971146376326,
      "hi": 0.9768856355855343,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "all",
      "target": "self",
      "value": 0.9313725490196079,
      "lo": 0.8745972304693189,
      "hi": 0.9747732037541391,
      "n": 98,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "all",
      "target": "self",
      "value": 0.9666666666666667,
      "lo": 0.917419662440894,
      "hi": 0.9869624489016494,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 1,
      "lo": 0.8864866068260312,
      "hi": 0.9999999999999999,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9565217391304348,
      "lo": 0.8934831434470112,
      "hi": 0.9829642837269863,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9583333333333334,
      "lo": 0.8977180853334191,
      "hi": 0.9836792924637118,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9479166666666666,
      "lo": 0.8838152196850738,
      "hi": 0.9775503995257587,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9479166666666666,
      "lo": 0.8838152196850738,
      "hi": 0.9775503995257587,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9505703422053232,
      "lo": 0.9076231567195422,
      "hi": 0.9850760139821338,
      "n": 81,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.9583333333333334,
      "lo": 0.8977180853334191,
      "hi": 0.9836792924637118,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.7333333333333333,
      "lo": 0.48778924327704815,
      "hi": 1,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "base=cord",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "capture=photo",
      "target": "self",
      "value": 1,
      "lo": 0.9059421741627975,
      "hi": 1,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "capture=photo",
      "target": "self",
      "value": 1,
      "lo": 0.895730002457548,
      "hi": 1,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "capture=photo",
      "target": "self",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.963302752293578,
      "lo": 0.9094227992822939,
      "hi": 0.9856382984343681,
      "n": 109,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9642857142857143,
      "lo": 0.9117533615468005,
      "hi": 0.9860253876053231,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9464285714285714,
      "lo": 0.8880297362776991,
      "hi": 0.975219060983958,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "capture=photo",
      "target": "self",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9464285714285714,
      "lo": 0.8880297362776991,
      "hi": 0.975219060983958,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9492753623188406,
      "lo": 0.9065662846020761,
      "hi": 0.9827034056974925,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9642857142857143,
      "lo": 0.9117533615468005,
      "hi": 0.9860253876053231,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8063923194655637,
      "hi": 1,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.9146341463414634,
      "lo": 0.7619047619047619,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=genuine",
      "target": "self",
      "value": 1,
      "lo": 0.8241207763533425,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=genuine",
      "target": "self",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=genuine",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9420289855072463,
      "lo": 0.8602075664233835,
      "hi": 0.9772276111196287,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9420289855072463,
      "lo": 0.8602075664233835,
      "hi": 0.9772276111196287,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9130434782608695,
      "lo": 0.8229850166105782,
      "hi": 0.959536378798466,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9130434782608695,
      "lo": 0.8229850166105782,
      "hi": 0.959536378798466,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9202453987730062,
      "lo": 0.840258487654321,
      "hi": 0.9745263242763847,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.9420289855072463,
      "lo": 0.8602075664233835,
      "hi": 0.9772276111196287,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8532493994143954,
      "hi": 0.9711899371005063,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8532493994143954,
      "hi": 0.9711899371005063,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9392523364485982,
      "lo": 0.8861318876452863,
      "hi": 0.9823827020372045,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 1,
      "lo": 0.916201209134296,
      "hi": 0.9999999999999999,
      "n": 42,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 1,
      "lo": 0.9179901967742088,
      "hi": 1,
      "n": 43,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9646017699115044,
      "lo": 0.9125037991051361,
      "hi": 0.9861498214486251,
      "n": 113,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9658119658119658,
      "lo": 0.9153821514157074,
      "hi": 0.9866261581805496,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9487179487179487,
      "lo": 0.8926194657545686,
      "hi": 0.9762876214711834,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9487179487179487,
      "lo": 0.8926194657545686,
      "hi": 0.9762876214711834,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9295302013422819,
      "lo": 0.8692688777638715,
      "hi": 0.9735164477255455,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9658119658119658,
      "lo": 0.9153821514157074,
      "hi": 0.9866261581805496,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.95,
      "lo": 0.8518055555555556,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.8668077490609515,
      "hi": 0.9999999999999999,
      "n": 25,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.9411764705882353,
      "lo": 0.8484848484848485,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8532493994143954,
      "hi": 0.9711899371005063,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8532493994143954,
      "hi": 0.9711899371005063,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9392523364485982,
      "lo": 0.8842105263157894,
      "hi": 0.9822241887905605,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.8627450980392157,
      "lo": 0.6274509803921569,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=free",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.9104477611940298,
      "lo": 0.7352941176470589,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=none",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=none",
      "target": "self",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=none",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.95,
      "lo": 0.8783772379535698,
      "hi": 0.9803864454644556,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.95,
      "lo": 0.8783772379535698,
      "hi": 0.9803864454644556,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.925,
      "lo": 0.8458798391878072,
      "hi": 0.9651747507069949,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.925,
      "lo": 0.8458798391878072,
      "hi": 0.9651747507069949,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.93048128342246,
      "lo": 0.865977941599954,
      "hi": 0.9774196536074834,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.95,
      "lo": 0.8783772379535698,
      "hi": 0.9803864454644556,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.9615384615384616,
      "lo": 0.8979591836734694,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8407464268680283,
      "hi": 0.9737713012754938,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8407464268680283,
      "hi": 0.9737713012754938,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.9166666666666666,
      "lo": 0.8193105798166558,
      "hi": 0.9638795433982692,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.9166666666666666,
      "lo": 0.8193105798166558,
      "hi": 0.9638795433982692,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.93048128342246,
      "lo": 0.8674006964991752,
      "hi": 0.9802004584694922,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.9333333333333333,
      "lo": 0.8407464268680283,
      "hi": 0.9737713012754938,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.825,
      "lo": 0.574468085106383,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8977272727272727,
      "lo": 0.7972573379831445,
      "hi": 0.9770114942528736,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.9534883720930233,
      "lo": 0.8611111111111112,
      "hi": 1,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "all",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "all",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "all",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "all",
      "target": "self",
      "value": 0.6666666666666666,
      "lo": 0.5783110162063498,
      "hi": 0.7446825949874156,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.6979166666666666,
      "lo": 0.5999149981303159,
      "hi": 0.7806884150093544,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "base=cord",
      "target": "self",
      "value": 0.7857142857142857,
      "lo": 0.524107694133997,
      "hi": 0.9242861328730683,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.6964285714285714,
      "lo": 0.6059310267363951,
      "hi": 0.773898444058734,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.6521739130434783,
      "lo": 0.5344787754895757,
      "hi": 0.7538185807137565,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0.45454545454545453,
      "lo": 0.21271271622459764,
      "hi": 0.719908462590678,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.64,
      "lo": 0.5270066131909779,
      "hi": 0.7393507109138366,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.22809537235419838,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.7307692307692307,
      "lo": 0.5391695962082381,
      "hi": 0.8629555167798162,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.6666666666666666,
      "lo": 0.5771523809129953,
      "hi": 0.745584537199427,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.7419354838709677,
      "lo": 0.5675386419056621,
      "hi": 0.8629829409360625,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "lang=id",
      "target": "self",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.64,
      "lo": 0.5270066131909779,
      "hi": 0.7393507109138366,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.625,
      "lo": 0.5154872546314301,
      "hi": 0.7230582129846882,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "source=cord",
      "target": "self",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.6,
      "lo": 0.4736605349204075,
      "hi": 0.7143050946511744,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.8620689655172413,
      "lo": 0.6944100627964798,
      "hi": 0.9450256003588804,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.25925925925925924,
      "lo": 0.1317037456190719,
      "hi": 0.44678571314553067,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "all",
      "target": "self",
      "value": 0.81453125,
      "lo": 0.72514453125,
      "hi": 0.89625390625,
      "n": 120,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "all",
      "target": "self",
      "value": 0.525,
      "lo": 0.375,
      "hi": 0.675,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "all",
      "target": "self",
      "value": 0.55,
      "lo": 0.4,
      "hi": 0.75,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "all",
      "target": "self",
      "value": 0.65,
      "lo": 0.45,
      "hi": 0.7756249999999966,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "all",
      "target": "self",
      "value": 0.65,
      "lo": 0.49505880837257693,
      "hi": 0.7786547112682372,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "all",
      "target": "self",
      "value": 0.25,
      "lo": 0.16806231857542375,
      "hi": 0.3548467461923397,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "all",
      "target": "self",
      "value": 0.525,
      "lo": 0.3749736210669248,
      "hi": 0.670645298873211,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "all",
      "target": "self",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "base=cord",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "base=cord",
      "target": "self",
      "value": 0.5,
      "lo": 0.26799202452413634,
      "hi": 0.7320079754758637,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.8373609512850019,
      "lo": 0.7377972765630993,
      "hi": 0.9236718450326045,
      "n": 112,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.5757575757575758,
      "lo": 0.42424242424242425,
      "hi": 0.7575757575757576,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.6060606060606061,
      "lo": 0.45454545454545453,
      "hi": 0.8181818181818182,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.7272727272727273,
      "lo": 0.5151515151515151,
      "hi": 0.8492424242424201,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.7272727272727273,
      "lo": 0.5578244099712737,
      "hi": 0.8493255911457935,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.24050632911392406,
      "lo": 0.15972180097616331,
      "hi": 0.345356929122708,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.5757575757575758,
      "lo": 0.4080726333731245,
      "hi": 0.7276440336658979,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.012658227848101266,
      "lo": 0.0022379938550498787,
      "hi": 0.06827571876965954,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.7444444444444445,
      "lo": 0.574388888888889,
      "hi": 0.8933333333333333,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.26666666666666666,
      "hi": 0.7333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.26666666666666666,
      "hi": 0.8,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.6,
      "lo": 0.26666666666666666,
      "hi": 0.8,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.6,
      "lo": 0.357468301206246,
      "hi": 0.8017550385865841,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.31666666666666665,
      "lo": 0.21305867552366523,
      "hi": 0.44233767026176773,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.24809535365737387,
      "hi": 0.698830199745016,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.9791666666666666,
      "lo": 0.9166666666666666,
      "hi": 1,
      "n": 26,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.05555555555555555,
      "lo": 0.009875190978303097,
      "hi": 0.25757300781872594,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.8158783783783784,
      "lo": 0.7205912162162162,
      "hi": 0.901697635135135,
      "n": 117,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.5405405405405406,
      "lo": 0.3783783783783784,
      "hi": 0.7027027027027027,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.5675675675675675,
      "lo": 0.40540540540540543,
      "hi": 0.7837837837837838,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.6756756756756757,
      "lo": 0.4864864864864865,
      "hi": 0.8108108108108109,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.6756756756756757,
      "lo": 0.514636672419722,
      "hi": 0.8036673347185581,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.25,
      "lo": 0.16806231857542375,
      "hi": 0.3548467461923397,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.5405405405405406,
      "lo": 0.3838404689217949,
      "hi": 0.6896143019562697,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "editedField=total",
      "target": "self",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.6666666666666666,
      "lo": 0.39062208887279953,
      "hi": 0.8618799089087867,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.9254385964912281,
      "lo": 0.8047697368421054,
      "hi": 1,
      "n": 31,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.5,
      "lo": 0.25,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.5,
      "lo": 0.25,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.8333333333333334,
      "lo": 0.3333333333333333,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.05263157894736842,
      "lo": 0.009351994062300362,
      "hi": 0.24638731166898786,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.5,
      "lo": 0.2537815976337061,
      "hi": 0.7462184023662939,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.7444444444444445,
      "lo": 0.5721944444444444,
      "hi": 0.9005694444444443,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.2,
      "hi": 0.7333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.2650000000000029,
      "hi": 0.8,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.6,
      "lo": 0.26666666666666666,
      "hi": 0.8,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.6,
      "lo": 0.357468301206246,
      "hi": 0.8017550385865841,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.31666666666666665,
      "lo": 0.21305867552366523,
      "hi": 0.44233767026176773,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.4666666666666667,
      "lo": 0.24809535365737387,
      "hi": 0.698830199745016,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.31666666666666665,
      "lo": 0.21305867552366523,
      "hi": 0.44233767026176773,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.05,
      "lo": 0.008881448800795402,
      "hi": 0.23613119344674205,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.4482758620689655,
      "lo": 0.28413168023037194,
      "hi": 0.6245203678902909,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.14814814814814814,
      "lo": 0.05915927776244326,
      "hi": 0.3247868542781298,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.4,
      "lo": 0.21880653237281705,
      "hi": 0.6134184992377469,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.15,
      "lo": 0.052368745896216595,
      "hi": 0.36041886474075696,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.25,
      "lo": 0.16806231857542375,
      "hi": 0.3548467461923397,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.775625,
      "lo": 0.6487187500000001,
      "hi": 0.8943984374999999,
      "n": 100,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.5,
      "lo": 0.3,
      "hi": 0.7,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.5,
      "lo": 0.3,
      "hi": 0.75,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.55,
      "lo": 0.3,
      "hi": 0.75,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.55,
      "lo": 0.34208534245034233,
      "hi": 0.7418021417443759,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.5,
      "lo": 0.2992980081982123,
      "hi": 0.7007019918017877,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.913125,
      "lo": 0.771859375,
      "hi": 0.99625,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.6,
      "lo": 0.3,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.9,
      "lo": 0.5,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.79375,
      "lo": 0.614359375,
      "hi": 0.9475312499999998,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.5,
      "lo": 0.2,
      "hi": 0.8,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.5,
      "lo": 0.2,
      "hi": 0.8,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.6,
      "lo": 0.3,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.7509615384615385,
      "lo": 0.6310036057692308,
      "hi": 0.855324519230769,
      "n": 106,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.46153846153846156,
      "lo": 0.2692307692307692,
      "hi": 0.6538461538461539,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.46153846153846156,
      "lo": 0.2692307692307692,
      "hi": 0.6538461538461539,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.5,
      "lo": 0.3076923076923077,
      "hi": 0.6923076923076923,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.5,
      "lo": 0.3206059352575905,
      "hi": 0.6793940647424095,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.46153846153846156,
      "lo": 0.2875585353039122,
      "hi": 0.6454206125314121,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.9325892857142857,
      "lo": 0.8298883928571429,
      "hi": 0.9946428571428572,
      "n": 94,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.35714285714285715,
      "hi": 0.9285714285714286,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.7142857142857143,
      "lo": 0.42857142857142855,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.9285714285714286,
      "lo": 0.6428571428571429,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "all",
      "target": "self",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "all",
      "target": "self",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "all",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "all",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.07134759913335872,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.6666666666666666,
      "lo": 0.4670631683813174,
      "hi": 0.8202780967270225,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.08333333333333333,
      "lo": 0.023158815297043306,
      "hi": 0.25848802193210685,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.06313883485297894,
      "n": 57,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "currency=USD",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.1936076805344365,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "lang=en",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.1843181350088518,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "lang=id",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "lang=id",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "source=cord",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "source=cord",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.2,
      "lo": 0.05668215145437519,
      "hi": 0.5098375284633583,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.154639018924847,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.20388330103584862,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "all",
      "target": "self",
      "value": 4391,
      "lo": 4391,
      "hi": 4391,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "all",
      "target": "self",
      "value": 39704,
      "lo": 39704,
      "hi": 39704,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "all",
      "target": "self",
      "value": 66346.95,
      "lo": 66346.95,
      "hi": 66346.95,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "all",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 146,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "all",
      "target": "self",
      "value": 0.00342903595890411,
      "lo": 0.00342903595890411,
      "hi": 0.00342903595890411,
      "n": 146,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "all",
      "target": "self",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "all",
      "target": "self",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "all",
      "target": "self",
      "value": 0.02666666666666667,
      "lo": 0.010417940822967993,
      "hi": 0.06655389051214453,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 4342,
      "lo": 4342,
      "hi": 4342,
      "n": 122,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 39705.29999999998,
      "lo": 39705.29999999998,
      "hi": 39705.29999999998,
      "n": 122,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 64762.61999999995,
      "lo": 64762.61999999995,
      "hi": 64762.61999999995,
      "n": 122,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 122,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.0034042069672131146,
      "lo": 0.0034042069672131146,
      "hi": 0.0034042069672131146,
      "n": 122,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=consistent",
      "target": "self",
      "value": 0.031746031746031744,
      "lo": 0.012413278972689408,
      "hi": 0.07878608776460755,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 4500.5,
      "lo": 4500.5,
      "hi": 4500.5,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 28824.199999999997,
      "lo": 28824.199999999997,
      "hi": 28824.199999999997,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 35725.63999999999,
      "lo": 35725.63999999999,
      "hi": 35725.63999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0.003518892857142857,
      "lo": 0.003518892857142857,
      "hi": 0.003518892857142857,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 4382,
      "lo": 4382,
      "hi": 4382,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 58275.94999999997,
      "lo": 58275.94999999997,
      "hi": 58275.94999999997,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 70612.79000000001,
      "lo": 70612.79000000001,
      "hi": 70612.79000000001,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0.0036061500000000002,
      "lo": 0.0036061500000000002,
      "hi": 0.0036061500000000002,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=unknown",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "base=cord",
      "target": "self",
      "value": 5387.5,
      "lo": 5387.5,
      "hi": 5387.5,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "base=cord",
      "target": "self",
      "value": 43498.049999999996,
      "lo": 43498.049999999996,
      "hi": 43498.049999999996,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "base=cord",
      "target": "self",
      "value": 45662.81,
      "lo": 45662.81,
      "hi": 45662.81,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "base=cord",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "base=cord",
      "target": "self",
      "value": 0.0032951785714285717,
      "lo": 0.0032951785714285717,
      "hi": 0.0032951785714285717,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "base=cord",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "base=cord",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "base=cord",
      "target": "self",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "capture=photo",
      "target": "self",
      "value": 4367.5,
      "lo": 4367.5,
      "hi": 4367.5,
      "n": 132,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "capture=photo",
      "target": "self",
      "value": 40169.49999999999,
      "lo": 40169.49999999999,
      "hi": 40169.49999999999,
      "n": 132,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "capture=photo",
      "target": "self",
      "value": 66398.61,
      "lo": 66398.61,
      "hi": 66398.61,
      "n": 132,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 132,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.003413761363636364,
      "lo": 0.003413761363636364,
      "hi": 0.003413761363636364,
      "n": 132,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "capture=photo",
      "target": "self",
      "value": 0.029411764705882353,
      "lo": 0.011495862973155337,
      "hi": 0.07318187795256928,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 4505,
      "lo": 4505,
      "hi": 4505,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 25857.550000000003,
      "lo": 25857.550000000003,
      "hi": 25857.550000000003,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 28221.909999999996,
      "lo": 28221.909999999996,
      "hi": 28221.909999999996,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0.0036254250000000003,
      "lo": 0.0036254250000000003,
      "hi": 0.0036254250000000003,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_full",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 4878.5,
      "lo": 4878.5,
      "hi": 4878.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 39975.49999999999,
      "lo": 39975.49999999999,
      "hi": 39975.49999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 41627.9,
      "lo": 41627.9,
      "hi": 41627.9,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0.0034693500000000004,
      "lo": 0.0034693500000000004,
      "hi": 0.0034693500000000004,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_inpaint",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 4280.5,
      "lo": 4280.5,
      "hi": 4280.5,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 49266.399999999936,
      "lo": 49266.399999999936,
      "hi": 49266.399999999936,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 64498.37000000001,
      "lo": 64498.37000000001,
      "hi": 64498.37000000001,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0.0034116999999999997,
      "lo": 0.0034116999999999997,
      "hi": 0.0034116999999999997,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=duplicate",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=genuine",
      "target": "self",
      "value": 4351,
      "lo": 4351,
      "hi": 4351,
      "n": 65,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=genuine",
      "target": "self",
      "value": 39138.799999999996,
      "lo": 39138.799999999996,
      "hi": 39138.799999999996,
      "n": 65,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=genuine",
      "target": "self",
      "value": 68863.08,
      "lo": 68863.08,
      "hi": 68863.08,
      "n": 65,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 65,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.0034246961538461533,
      "lo": 0.0034246961538461533,
      "hi": 0.0034246961538461533,
      "n": 65,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=genuine",
      "target": "self",
      "value": 0.057971014492753624,
      "lo": 0.02277238888037121,
      "hi": 0.13979243357661653,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 3792,
      "lo": 3792,
      "hi": 3792,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 5809,
      "lo": 5809,
      "hi": 5809,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 5897.8,
      "lo": 5897.8,
      "hi": 5897.8,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0.003265568181818182,
      "lo": 0.003265568181818182,
      "hi": 0.003265568181818182,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=hard_negative",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 4680.5,
      "lo": 4680.5,
      "hi": 4680.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 43693.899999999994,
      "lo": 43693.899999999994,
      "hi": 43693.899999999994,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 45701.98,
      "lo": 45701.98,
      "hi": 45701.98,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0.003255975,
      "lo": 0.003255975,
      "hi": 0.003255975,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=manual_edit",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 4333,
      "lo": 4333,
      "hi": 4333,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 39673.50000000001,
      "lo": 39673.50000000001,
      "hi": 39673.50000000001,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 67201.42,
      "lo": 67201.42,
      "hi": 67201.42,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 87,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.003374931034482759,
      "lo": 0.003374931034482759,
      "hi": 0.003374931034482759,
      "n": 87,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=IDR",
      "target": "self",
      "value": 0.04395604395604396,
      "lo": 0.01722436644411733,
      "hi": 0.10763093384266353,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=USD",
      "target": "self",
      "value": 4391,
      "lo": 4391,
      "hi": 4391,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=USD",
      "target": "self",
      "value": 40784.49999999994,
      "lo": 40784.49999999994,
      "hi": 40784.49999999994,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=USD",
      "target": "self",
      "value": 63803.67,
      "lo": 63803.67,
      "hi": 63803.67,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0.0034407562500000004,
      "lo": 0.0034407562500000004,
      "hi": 0.0034407562500000004,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=USD",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 4384,
      "lo": 4384,
      "hi": 4384,
      "n": 143,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 39759.200000000004,
      "lo": 39759.200000000004,
      "hi": 39759.200000000004,
      "n": 143,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 66358.02,
      "lo": 66358.02,
      "hi": 66358.02,
      "n": 143,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 143,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.0034258216783216787,
      "lo": 0.0034258216783216787,
      "hi": 0.0034258216783216787,
      "n": 143,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "docType=receipt",
      "target": "self",
      "value": 0.027210884353741496,
      "lo": 0.010631557432044515,
      "hi": 0.06787112288723109,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "editedField=total",
      "target": "self",
      "value": 4714.5,
      "lo": 4714.5,
      "hi": 4714.5,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "editedField=total",
      "target": "self",
      "value": 30151.39999999999,
      "lo": 30151.39999999999,
      "hi": 30151.39999999999,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "editedField=total",
      "target": "self",
      "value": 35991.08000000001,
      "lo": 35991.08000000001,
      "hi": 35991.08000000001,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0.0034891875000000005,
      "lo": 0.0034891875000000005,
      "hi": 0.0034891875000000005,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "editedField=total",
      "target": "self",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=en",
      "target": "self",
      "value": 4460,
      "lo": 4460,
      "hi": 4460,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=en",
      "target": "self",
      "value": 39722.4,
      "lo": 39722.4,
      "hi": 39722.4,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=en",
      "target": "self",
      "value": 63456.320000000014,
      "lo": 63456.320000000014,
      "hi": 63456.320000000014,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=en",
      "target": "self",
      "value": 0.00347785,
      "lo": 0.00347785,
      "hi": 0.00347785,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=en",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=id",
      "target": "self",
      "value": 4333,
      "lo": 4333,
      "hi": 4333,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=id",
      "target": "self",
      "value": 39673.50000000001,
      "lo": 39673.50000000001,
      "hi": 39673.50000000001,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=id",
      "target": "self",
      "value": 67201.42,
      "lo": 67201.42,
      "hi": 67201.42,
      "n": 87,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 87,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.003374931034482759,
      "lo": 0.003374931034482759,
      "hi": 0.003374931034482759,
      "n": 87,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=id",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=id",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=id",
      "target": "self",
      "value": 0.04395604395604396,
      "lo": 0.01722436644411733,
      "hi": 0.10763093384266353,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 4505,
      "lo": 4505,
      "hi": 4505,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 27413.049999999996,
      "lo": 27413.049999999996,
      "hi": 27413.049999999996,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 28533.010000000002,
      "lo": 28533.010000000002,
      "hi": 28533.010000000002,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0.0035526750000000004,
      "lo": 0.0035526750000000004,
      "hi": 0.0035526750000000004,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=free",
      "target": "self",
      "value": 4491.5,
      "lo": 4491.5,
      "hi": 4491.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=free",
      "target": "self",
      "value": 5662.499999999999,
      "lo": 5662.499999999999,
      "hi": 5662.499999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=free",
      "target": "self",
      "value": 5860.5,
      "lo": 5860.5,
      "hi": 5860.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0.0036981749999999993,
      "lo": 0.0036981749999999993,
      "hi": 0.0036981749999999993,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=free",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 4556,
      "lo": 4556,
      "hi": 4556,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 29403.65000000001,
      "lo": 29403.65000000001,
      "hi": 29403.65000000001,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 38381.529999999984,
      "lo": 38381.529999999984,
      "hi": 38381.529999999984,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0.0035157375,
      "lo": 0.0035157375,
      "hi": 0.0035157375,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=intact",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=none",
      "target": "self",
      "value": 4293,
      "lo": 4293,
      "hi": 4293,
      "n": 106,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=none",
      "target": "self",
      "value": 39066.5,
      "lo": 39066.5,
      "hi": 39066.5,
      "n": 106,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=none",
      "target": "self",
      "value": 66494.55,
      "lo": 66494.55,
      "hi": 66494.55,
      "n": 106,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 106,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.0034045047169811316,
      "lo": 0.0034045047169811316,
      "hi": 0.0034045047169811316,
      "n": 106,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=none",
      "target": "self",
      "value": 0.03636363636363636,
      "lo": 0.014230310826517947,
      "hi": 0.08978679281359792,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 4643,
      "lo": 4643,
      "hi": 4643,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 42249.15,
      "lo": 42249.15,
      "hi": 42249.15,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 45413.02999999999,
      "lo": 45413.02999999999,
      "hi": 45413.02999999999,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0.00347235,
      "lo": 0.00347235,
      "hi": 0.00347235,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=stripped",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=cord",
      "target": "self",
      "value": 4255,
      "lo": 4255,
      "hi": 4255,
      "n": 72,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=cord",
      "target": "self",
      "value": 30281.600000000013,
      "lo": 30281.600000000013,
      "hi": 30281.600000000013,
      "n": 72,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=cord",
      "target": "self",
      "value": 68334.37000000005,
      "lo": 68334.37000000005,
      "hi": 68334.37000000005,
      "n": 72,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 72,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.0033867187499999995,
      "lo": 0.0033867187499999995,
      "hi": 0.0033867187499999995,
      "n": 72,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=cord",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=cord",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=cord",
      "target": "self",
      "value": 0.05263157894736842,
      "lo": 0.020655429299384284,
      "hi": 0.12765672575889647,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 4680.5,
      "lo": 4680.5,
      "hi": 4680.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 43693.899999999994,
      "lo": 43693.899999999994,
      "hi": 43693.899999999994,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 45701.98,
      "lo": 45701.98,
      "hi": 45701.98,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0.003255975,
      "lo": 0.003255975,
      "hi": 0.003255975,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 4429,
      "lo": 4429,
      "hi": 4429,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 46715.499999999956,
      "lo": 46715.499999999956,
      "hi": 46715.499999999956,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 64220.49000000001,
      "lo": 64220.49000000001,
      "hi": 64220.49000000001,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0.0034421691176470593,
      "lo": 0.0034421691176470593,
      "hi": 0.0034421691176470593,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=expressexpense",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 4660.5,
      "lo": 4660.5,
      "hi": 4660.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 14335.449999999984,
      "lo": 14335.449999999984,
      "hi": 14335.449999999984,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 19850.29,
      "lo": 19850.29,
      "hi": 19850.29,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0.003648975,
      "lo": 0.003648975,
      "hi": 0.003648975,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 4403.5,
      "lo": 4403.5,
      "hi": 4403.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 27413.049999999996,
      "lo": 27413.049999999996,
      "hi": 27413.049999999996,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 28533.010000000002,
      "lo": 28533.010000000002,
      "hi": 28533.010000000002,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0.003601875,
      "lo": 0.003601875,
      "hi": 0.003601875,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 4428,
      "lo": 4428,
      "hi": 4428,
      "n": 35,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 26753.699999999975,
      "lo": 26753.699999999975,
      "hi": 26753.699999999975,
      "n": 35,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 35383.61999999999,
      "lo": 35383.61999999999,
      "hi": 35383.61999999999,
      "n": 35,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 35,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.0034665857142857142,
      "lo": 0.0034665857142857142,
      "hi": 0.0034665857142857142,
      "n": 35,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=exclusive",
      "target": "self",
      "value": 0.10256410256410256,
      "lo": 0.04061331344668381,
      "hi": 0.23578854462856527,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 3994,
      "lo": 3994,
      "hi": 3994,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 14683.999999999967,
      "lo": 14683.999999999967,
      "hi": 14683.999999999967,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 53990.07999999999,
      "lo": 53990.07999999999,
      "hi": 53990.07999999999,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0.003256250000000001,
      "lo": 0.003256250000000001,
      "hi": 0.003256250000000001,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=none",
      "target": "self",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9213484012671117,
      "hi": 1,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9123783988027135,
      "hi": 1,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9229264369144198,
      "hi": 1,
      "n": 46,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9679454935003613,
      "hi": 1,
      "n": 116,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9689808335812966,
      "hi": 1,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.9833333333333333,
      "lo": 0.941264037027841,
      "hi": 0.9954174354340789,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8620237953250198,
      "hi": 1,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.9833333333333333,
      "lo": 0.941264037027841,
      "hi": 0.9954174354340789,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.937799043062201,
      "lo": 0.8808203930298731,
      "hi": 0.9785982609216217,
      "n": 98,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "all",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9689808335812966,
      "hi": 1,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8864866068260312,
      "hi": 0.9999999999999999,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9599186107143782,
      "hi": 1,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9615244121423243,
      "hi": 1,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.9895833333333334,
      "lo": 0.9433338237728424,
      "hi": 0.9981588297831838,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.9895833333333334,
      "lo": 0.9433338237728424,
      "hi": 0.9981588297831838,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.9463955637707948,
      "lo": 0.8875957317642664,
      "hi": 0.9883743291592129,
      "n": 81,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9615244121423243,
      "hi": 1,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.8333333333333334,
      "lo": 0.6923076923076923,
      "hi": 0.9666666666666667,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.9545454545454546,
      "lo": 0.8333333333333334,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9059421741627975,
      "hi": 1,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.895730002457548,
      "hi": 1,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9659570262486751,
      "hi": 1,
      "n": 109,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9668386529330562,
      "hi": 1,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.9821428571428571,
      "lo": 0.9372195125788385,
      "hi": 0.9950891884637512,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.9821428571428571,
      "lo": 0.9372195125788385,
      "hi": 0.9950891884637512,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.9417989417989417,
      "lo": 0.8821646969073164,
      "hi": 0.9843478260869565,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9668386529330562,
      "hi": 1,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8063923194655637,
      "hi": 1,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.9146341463414634,
      "lo": 0.8192497261774371,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8241207763533425,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9472627418109483,
      "hi": 1,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9472627418109483,
      "hi": 1,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.9710144927536232,
      "lo": 0.9003341623693445,
      "hi": 0.9920147973076358,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.9710144927536232,
      "lo": 0.9003341623693445,
      "hi": 0.9920147973076358,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.9384164222873901,
      "lo": 0.8437446853741497,
      "hi": 0.993976805425294,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9472627418109483,
      "hi": 1,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.9230769230769231,
      "lo": 0.7142857142857143,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.9480812641083521,
      "lo": 0.8720146725486851,
      "hi": 0.9916683884297521,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.916201209134296,
      "hi": 0.9999999999999999,
      "n": 42,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9179901967742088,
      "hi": 1,
      "n": 43,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.967122467834048,
      "hi": 1,
      "n": 113,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9682107543372667,
      "hi": 1,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.9829059829059829,
      "lo": 0.9398099145713432,
      "hi": 0.9952996173954185,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.9829059829059829,
      "lo": 0.9398099145713432,
      "hi": 0.9952996173954185,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.9361702127659575,
      "lo": 0.877547728768927,
      "hi": 0.9779286926994907,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9682107543372667,
      "hi": 1,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.75,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8668077490609515,
      "hi": 0.9999999999999999,
      "n": 25,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.8529411764705882,
      "lo": 0.6875,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.9480812641083521,
      "lo": 0.8738266406490706,
      "hi": 0.9918707415819097,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.9411764705882353,
      "lo": 0.8362878787878789,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.9253731343283582,
      "lo": 0.8285714285714286,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9541818704644728,
      "hi": 0.9999999999999999,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9541818704644728,
      "hi": 0.9999999999999999,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.975,
      "lo": 0.9133556701442198,
      "hi": 0.9931171067970292,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.975,
      "lo": 0.9133556701442198,
      "hi": 0.9931171067970292,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.9460154241645244,
      "lo": 0.8618740449041966,
      "hi": 0.9946815546549589,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.9541818704644728,
      "hi": 0.9999999999999999,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0.9230769230769231,
      "lo": 0.8181818181818182,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.93982814785791,
      "hi": 0.9999999999999998,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.93982814785791,
      "hi": 0.9999999999999998,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.9833333333333333,
      "lo": 0.9114487027240993,
      "hi": 0.9970518402052136,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.9833333333333333,
      "lo": 0.9114487027240993,
      "hi": 0.9970518402052136,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.9460154241645244,
      "lo": 0.8659782485555682,
      "hi": 0.9940493697478991,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.93982814785791,
      "hi": 0.9999999999999998,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.9230769230769231,
      "lo": 0.7272727272727273,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.875,
      "lo": 0.7291193181818182,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0.9109947643979057,
      "lo": 0.7652594908931315,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.9767441860465116,
      "lo": 0.9347683066361556,
      "hi": 1,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.6128485756752643,
      "hi": 0.7747437577572543,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.7395833333333334,
      "lo": 0.6437894471878516,
      "hi": 0.8169410002970126,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.7857142857142857,
      "lo": 0.524107694133997,
      "hi": 0.9242861328730683,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.7321428571428571,
      "lo": 0.6434352838771962,
      "hi": 0.8054540906988654,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.7101449275362319,
      "lo": 0.5942855002638685,
      "hi": 0.8038394202073997,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0.45454545454545453,
      "lo": 0.21271271622459764,
      "hi": 0.719908462590678,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.6933333333333334,
      "lo": 0.5816954517744293,
      "hi": 0.7861313291322192,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.22809537235419838,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.7307692307692307,
      "lo": 0.5391695962082381,
      "hi": 0.8629555167798162,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.precision",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.7008547008547008,
      "lo": 0.6125818390957586,
      "hi": 0.7763575237576733,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "totals_add_up.recall",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.46769466506643426,
      "hi": 0.9110583316059453,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.7419354838709677,
      "lo": 0.5675386419056621,
      "hi": 0.8629829409360625,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.6933333333333334,
      "lo": 0.5816954517744293,
      "hi": 0.7861313291322192,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.05202306241026692,
      "n": 70,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.675,
      "lo": 0.5664052731061473,
      "hi": 0.7675583815564182,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.06419393671876342,
      "n": 56,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.6666666666666666,
      "lo": 0.5405686645211968,
      "hi": 0.7727073847647731,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "checks",
      "metric": "false_alarm_rate",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "checks",
      "metric": "coverage",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.25925925925925924,
      "lo": 0.1317037456190719,
      "hi": 0.44678571314553067,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.888125,
      "lo": 0.81578125,
      "hi": 0.95375390625,
      "n": 120,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.45,
      "lo": 0.3,
      "hi": 0.75,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.475,
      "hi": 0.9,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.8,
      "lo": 0.675,
      "hi": 0.925,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.475,
      "lo": 0.329354701126789,
      "hi": 0.6250263789330753,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.425,
      "lo": 0.28509392559950375,
      "hi": 0.5780493145800892,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.2857142857142857,
      "lo": 0.11721378644576919,
      "hi": 0.5464908432989318,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.21428571428571427,
      "lo": 0.07571386712693184,
      "hi": 0.47589230586600295,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.8954737245876486,
      "lo": 0.8081990794016111,
      "hi": 0.9635692366705024,
      "n": 112,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.48484848484848486,
      "lo": 0.3333333333333333,
      "hi": 0.8484848484848485,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.7878787878787878,
      "lo": 0.45454545454545453,
      "hi": 0.9393939393939394,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.8484848484848485,
      "lo": 0.696969696969697,
      "hi": 0.9696969696969697,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.5151515151515151,
      "lo": 0.3521837544891414,
      "hi": 0.674959578918663,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.012658227848101266,
      "lo": 0.0022379938550498787,
      "hi": 0.06827571876965954,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.45454545454545453,
      "lo": 0.29842938513876116,
      "hi": 0.6201406146378254,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04637121165392266,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.8988888888888888,
      "lo": 0.7805555555555556,
      "hi": 0.9916666666666667,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.26666666666666666,
      "lo": 0.06666666666666667,
      "hi": 0.8666666666666667,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.8666666666666667,
      "lo": 0.2,
      "hi": 1,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.8666666666666667,
      "lo": 0.6666666666666666,
      "hi": 1,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.26666666666666666,
      "lo": 0.10897453325692374,
      "hi": 0.5195043405598057,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.2,
      "lo": 0.07047549346981563,
      "hi": 0.45185448715169363,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.9861111111111112,
      "lo": 0.9375,
      "hi": 1,
      "n": 26,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.8991554054054054,
      "lo": 0.8195819256756757,
      "hi": 0.960308277027027,
      "n": 117,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.4594594594594595,
      "lo": 0.32432432432432434,
      "hi": 0.8108108108108109,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.7837837837837838,
      "lo": 0.5135135135135135,
      "hi": 0.918918918918919,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.8378378378378378,
      "lo": 0.7027027027027027,
      "hi": 0.9459459459459459,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.4864864864864865,
      "lo": 0.3344640430301664,
      "hi": 0.6410510333438121,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.43243243243243246,
      "lo": 0.28671719277157315,
      "hi": 0.5908581890983192,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.2537815976337061,
      "hi": 0.7462184023662939,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.4166666666666667,
      "lo": 0.19326031365875665,
      "hi": 0.6804886874504503,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.9254385964912281,
      "lo": 0.793859649122807,
      "hi": 1,
      "n": 31,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.5,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.5,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.75,
      "lo": 0.5,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.5833333333333334,
      "lo": 0.31951131254954973,
      "hi": 0.8067396863412435,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.2537815976337061,
      "hi": 0.7462184023662939,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.8988888888888888,
      "lo": 0.7810972222222222,
      "hi": 0.9888888888888889,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.26666666666666666,
      "lo": 0.06666666666666667,
      "hi": 0.8666666666666667,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.8666666666666667,
      "lo": 0.2,
      "hi": 1,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.8666666666666667,
      "lo": 0.6666666666666666,
      "hi": 1,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.26666666666666666,
      "lo": 0.10897453325692374,
      "hi": 0.5195043405598057,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.2,
      "lo": 0.07047549346981563,
      "hi": 0.45185448715169363,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.3,
      "lo": 0.10779126740630099,
      "hi": 0.6032218525388546,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.2,
      "lo": 0.05668215145437519,
      "hi": 0.5098375284633583,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.85,
      "lo": 0.6395811352592431,
      "hi": 0.9476312541037835,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0.05,
      "lo": 0.008881448800795402,
      "hi": 0.23613119344674205,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.850625,
      "lo": 0.7331093750000001,
      "hi": 0.9500078124999999,
      "n": 100,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.3,
      "hi": 0.7,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.65,
      "lo": 0.35,
      "hi": 0.85,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.7,
      "lo": 0.5,
      "hi": 0.9,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.2992980081982123,
      "hi": 0.7007019918017877,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.2992980081982123,
      "hi": 0.7007019918017877,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.93,
      "lo": 0.799375,
      "hi": 1,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.2,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.6,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.7,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.92125,
      "lo": 0.7906093750000001,
      "hi": 0.99625,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.3,
      "lo": 0.1,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.8,
      "lo": 0.3,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.9,
      "lo": 0.7,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.3,
      "lo": 0.10779126740630099,
      "hi": 0.6032218525388546,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.2,
      "lo": 0.05668215145437519,
      "hi": 0.5098375284633583,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.838701923076923,
      "lo": 0.7240384615384615,
      "hi": 0.9375120192307692,
      "n": 106,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.46153846153846156,
      "lo": 0.2692307692307692,
      "hi": 0.6923076923076923,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.6538461538461539,
      "lo": 0.38461538461538464,
      "hi": 0.8846153846153846,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.7307692307692307,
      "lo": 0.5384615384615384,
      "hi": 0.8846153846153846,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.46153846153846156,
      "lo": 0.2875585353039122,
      "hi": 0.6454206125314121,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.4230769230769231,
      "lo": 0.2554444331365656,
      "hi": 0.6105138625340828,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.9799107142857143,
      "lo": 0.9486495535714287,
      "hi": 1,
      "n": 94,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.42857142857142855,
      "lo": 0.21428571428571427,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.9285714285714286,
      "lo": 0.5714285714285714,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.9285714285714286,
      "lo": 0.7857142857142857,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.5,
      "lo": 0.26799202452413634,
      "hi": 0.7320079754758637,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.42857142857142855,
      "lo": 0.21380798904474121,
      "hi": 0.6740935542034926,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 6.938893903907228e-18,
      "hi": 0.07134759913335872,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.6666666666666666,
      "lo": 0.4670631683813174,
      "hi": 0.8202780967270225,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.08333333333333333,
      "lo": 0.023158815297043306,
      "hi": 0.25848802193210685,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.06313883485297894,
      "n": 57,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.1936076805344365,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.1843181350088518,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.6333333333333333,
      "lo": 0.4551356365479487,
      "hi": 0.7812607919389929,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.06666666666666667,
      "lo": 0.018477023791270378,
      "hi": 0.2132345836261692,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.14865487460862087,
      "n": 22,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.062117855787202914,
      "n": 58,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.3125,
      "lo": 0.14164643854782039,
      "hi": 0.5559564416525933,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.125,
      "lo": 0.03497748774324047,
      "hi": 0.36022827265758695,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "recall",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "recall_exact",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0.2,
      "lo": 0.05668215145437519,
      "hi": 0.5098375284633583,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.154639018924847,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "duplicates",
      "metric": "false_match_rate_genuine",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.20388330103584862,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "all",
      "target": "self-haiku",
      "value": 5403.5,
      "lo": 5403.5,
      "hi": 5403.5,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "all",
      "target": "self-haiku",
      "value": 8441.999999999998,
      "lo": 8441.999999999998,
      "hi": 8441.999999999998,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "all",
      "target": "self-haiku",
      "value": 10667.659999999998,
      "lo": 10667.659999999998,
      "hi": 10667.659999999998,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 150,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0.0008517233333333334,
      "lo": 0.0008517233333333334,
      "hi": 0.0008517233333333334,
      "n": 150,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "all",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 5226.5,
      "lo": 5226.5,
      "hi": 5226.5,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 8703.75,
      "lo": 8703.75,
      "hi": 8703.75,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 10707.5,
      "lo": 10707.5,
      "hi": 10707.5,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 126,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0.0008481190476190477,
      "lo": 0.0008481190476190477,
      "hi": 0.0008481190476190477,
      "n": 126,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=consistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 6181,
      "lo": 6181,
      "hi": 6181,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 7545.599999999999,
      "lo": 7545.599999999999,
      "hi": 7545.599999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 7730.719999999999,
      "lo": 7730.719999999999,
      "hi": 7730.719999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0.0009695571428571428,
      "lo": 0.0009695571428571428,
      "hi": 0.0009695571428571428,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 2861.5,
      "lo": 2861.5,
      "hi": 2861.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 6063.349999999999,
      "lo": 6063.349999999999,
      "hi": 6063.349999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 6235.07,
      "lo": 6235.07,
      "hi": 6235.07,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0.0007321700000000001,
      "lo": 0.0007321700000000001,
      "hi": 0.0007321700000000001,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=unknown",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 5682,
      "lo": 5682,
      "hi": 5682,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 7545.599999999999,
      "lo": 7545.599999999999,
      "hi": 7545.599999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 7730.719999999999,
      "lo": 7730.719999999999,
      "hi": 7730.719999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0.0008865428571428572,
      "lo": 0.0008865428571428572,
      "hi": 0.0008865428571428572,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "base=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 5326.5,
      "lo": 5326.5,
      "hi": 5326.5,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 8466.25,
      "lo": 8466.25,
      "hi": 8466.25,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 10690.900000000001,
      "lo": 10690.900000000001,
      "hi": 10690.900000000001,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 136,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0.000849354411764706,
      "lo": 0.000849354411764706,
      "hi": 0.000849354411764706,
      "n": 136,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "capture=photo",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 5403.5,
      "lo": 5403.5,
      "hi": 5403.5,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 7188.550000000001,
      "lo": 7188.550000000001,
      "hi": 7188.550000000001,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 8762.509999999997,
      "lo": 8762.509999999997,
      "hi": 8762.509999999997,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0.00090525,
      "lo": 0.00090525,
      "hi": 0.00090525,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_full",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 5454,
      "lo": 5454,
      "hi": 5454,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 7117.699999999999,
      "lo": 7117.699999999999,
      "hi": 7117.699999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 7360.34,
      "lo": 7360.34,
      "hi": 7360.34,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0.0008626500000000001,
      "lo": 0.0008626500000000001,
      "hi": 0.0008626500000000001,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_inpaint",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 5816,
      "lo": 5816,
      "hi": 5816,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 8650.75,
      "lo": 8650.75,
      "hi": 8650.75,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 8902.06,
      "lo": 8902.06,
      "hi": 8902.06,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0.00088488,
      "lo": 0.00088488,
      "hi": 0.00088488,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=duplicate",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 4788,
      "lo": 4788,
      "hi": 4788,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 8925.999999999995,
      "lo": 8925.999999999995,
      "hi": 8925.999999999995,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 10774.92,
      "lo": 10774.92,
      "hi": 10774.92,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 69,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0.0008227057971014494,
      "lo": 0.0008227057971014494,
      "hi": 0.0008227057971014494,
      "n": 69,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=genuine",
      "target": "self-haiku",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 3394,
      "lo": 3394,
      "hi": 3394,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 7913.5,
      "lo": 7913.5,
      "hi": 7913.5,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 7986.7,
      "lo": 7986.7,
      "hi": 7986.7,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0.0008147181818181818,
      "lo": 0.0008147181818181818,
      "hi": 0.0008147181818181818,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=hard_negative",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 5493.5,
      "lo": 5493.5,
      "hi": 5493.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 7137.0999999999985,
      "lo": 7137.0999999999985,
      "hi": 7137.0999999999985,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 7649.02,
      "lo": 7649.02,
      "hi": 7649.02,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0.0008751999999999999,
      "lo": 0.0008751999999999999,
      "hi": 0.0008751999999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=manual_edit",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 5517,
      "lo": 5517,
      "hi": 5517,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 8660.5,
      "lo": 8660.5,
      "hi": 8660.5,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 10757.1,
      "lo": 10757.1,
      "hi": 10757.1,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0.0008713428571428573,
      "lo": 0.0008713428571428573,
      "hi": 0.0008713428571428573,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=IDR",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 3869,
      "lo": 3869,
      "hi": 3869,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 7668.999999999997,
      "lo": 7668.999999999997,
      "hi": 7668.999999999997,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 8666.65,
      "lo": 8666.65,
      "hi": 8666.65,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0.0007866125,
      "lo": 0.0007866125,
      "hi": 0.0007866125,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=USD",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 5405,
      "lo": 5405,
      "hi": 5405,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 8462.999999999998,
      "lo": 8462.999999999998,
      "hi": 8462.999999999998,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 10672.64,
      "lo": 10672.64,
      "hi": 10672.64,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 147,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0.0008531775510204083,
      "lo": 0.0008531775510204083,
      "hi": 0.0008531775510204083,
      "n": 147,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "docType=receipt",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 6131,
      "lo": 6131,
      "hi": 6131,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 7581.2,
      "lo": 7581.2,
      "hi": 7581.2,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 7737.84,
      "lo": 7737.84,
      "hi": 7737.84,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0.0009461666666666667,
      "lo": 0.0009461666666666667,
      "hi": 0.0009461666666666667,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "editedField=total",
      "target": "self-haiku",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 3908,
      "lo": 3908,
      "hi": 3908,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 7548.999999999999,
      "lo": 7548.999999999999,
      "hi": 7548.999999999999,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 8653.400000000001,
      "lo": 8653.400000000001,
      "hi": 8653.400000000001,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0.00079324,
      "lo": 0.00079324,
      "hi": 0.00079324,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=en",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 5517,
      "lo": 5517,
      "hi": 5517,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 8660.5,
      "lo": 8660.5,
      "hi": 8660.5,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 10757.1,
      "lo": 10757.1,
      "hi": 10757.1,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0.0008713428571428573,
      "lo": 0.0008713428571428573,
      "hi": 0.0008713428571428573,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=id",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 4581.5,
      "lo": 4581.5,
      "hi": 4581.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 6470.749999999998,
      "lo": 6470.749999999998,
      "hi": 6470.749999999998,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 6962.15,
      "lo": 6962.15,
      "hi": 6962.15,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0.00084525,
      "lo": 0.00084525,
      "hi": 0.00084525,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 5680.5,
      "lo": 5680.5,
      "hi": 5680.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 8163.749999999998,
      "lo": 8163.749999999998,
      "hi": 8163.749999999998,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 8957.550000000001,
      "lo": 8957.550000000001,
      "hi": 8957.550000000001,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0.00096525,
      "lo": 0.00096525,
      "hi": 0.00096525,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=free",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 5636,
      "lo": 5636,
      "hi": 5636,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 7188.550000000001,
      "lo": 7188.550000000001,
      "hi": 7188.550000000001,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 8762.509999999997,
      "lo": 8762.509999999997,
      "hi": 8762.509999999997,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0.0009109949999999998,
      "lo": 0.0009109949999999998,
      "hi": 0.0009109949999999998,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=intact",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 5021,
      "lo": 5021,
      "hi": 5021,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 8650.75,
      "lo": 8650.75,
      "hi": 8650.75,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 10734.06,
      "lo": 10734.06,
      "hi": 10734.06,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 110,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0.0008388636363636365,
      "lo": 0.0008388636363636365,
      "hi": 0.0008388636363636365,
      "n": 110,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 5113,
      "lo": 5113,
      "hi": 5113,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 7438.8,
      "lo": 7438.8,
      "hi": 7438.8,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 7709.36,
      "lo": 7709.36,
      "hi": 7709.36,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0.0008631800000000001,
      "lo": 0.0008631800000000001,
      "hi": 0.0008631800000000001,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=stripped",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 5496,
      "lo": 5496,
      "hi": 5496,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 9042,
      "lo": 9042,
      "hi": 9042,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 10769.25,
      "lo": 10769.25,
      "hi": 10769.25,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 76,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0.0008701065789473684,
      "lo": 0.0008701065789473684,
      "hi": 0.0008701065789473684,
      "n": 76,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=cord",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 5493.5,
      "lo": 5493.5,
      "hi": 5493.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 7137.0999999999985,
      "lo": 7137.0999999999985,
      "hi": 7137.0999999999985,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 7649.02,
      "lo": 7649.02,
      "hi": 7649.02,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0.0008751999999999999,
      "lo": 0.0008751999999999999,
      "hi": 0.0008751999999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 3869,
      "lo": 3869,
      "hi": 3869,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 7932.999999999998,
      "lo": 7932.999999999998,
      "hi": 7932.999999999998,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 8682.550000000001,
      "lo": 8682.550000000001,
      "hi": 8682.550000000001,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0.0007690264705882353,
      "lo": 0.0007690264705882353,
      "hi": 0.0007690264705882353,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=expressexpense",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 5178,
      "lo": 5178,
      "hi": 5178,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 7967.549999999997,
      "lo": 7967.549999999997,
      "hi": 7967.549999999997,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 8918.310000000001,
      "lo": 8918.310000000001,
      "hi": 8918.310000000001,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0.0008809499999999998,
      "lo": 0.0008809499999999998,
      "hi": 0.0008809499999999998,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 5445.5,
      "lo": 5445.5,
      "hi": 5445.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 7024.7,
      "lo": 7024.7,
      "hi": 7024.7,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 7072.94,
      "lo": 7072.94,
      "hi": 7072.94,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0.00092955,
      "lo": 0.00092955,
      "hi": 0.00092955,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 5873,
      "lo": 5873,
      "hi": 5873,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 9118.700000000003,
      "lo": 9118.700000000003,
      "hi": 9118.700000000003,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 10685.92,
      "lo": 10685.92,
      "hi": 10685.92,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0.0009104897435897433,
      "lo": 0.0009104897435897433,
      "hi": 0.0009104897435897433,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=exclusive",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 5420,
      "lo": 5420,
      "hi": 5420,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 8738.999999999998,
      "lo": 8738.999999999998,
      "hi": 8738.999999999998,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 10340.4,
      "lo": 10340.4,
      "hi": 10340.4,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.01633333333333333,
      "lo": 0.01633333333333333,
      "hi": 0.01633333333333333,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0.0008352999999999998,
      "lo": 0.0008352999999999998,
      "hi": 0.0008352999999999998,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=none",
      "target": "self-haiku",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9213484012671117,
      "hi": 1,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9123783988027135,
      "hi": 1,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8478260869565217,
      "lo": 0.71775860447939,
      "hi": 0.9242771777219454,
      "n": 46,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9310344827586207,
      "lo": 0.8697932609096686,
      "hi": 0.9646425093492634,
      "n": 116,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9666666666666667,
      "lo": 0.917419662440894,
      "hi": 0.9869624489016494,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9583333333333334,
      "lo": 0.9061591476629647,
      "hi": 0.9820732831198906,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8620237953250198,
      "hi": 1,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8333333333333334,
      "lo": 0.7565471860673773,
      "hi": 0.8894400363201539,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9122807017543859,
      "lo": 0.8460155040524543,
      "hi": 0.9560857595934126,
      "n": 98,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9689808335812966,
      "hi": 1,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8864866068260312,
      "hi": 0.9999999999999999,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9117647058823529,
      "lo": 0.7703951343719113,
      "hi": 0.9695340563253514,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9456521739130435,
      "lo": 0.8790146952375347,
      "hi": 0.9765649360513676,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9583333333333334,
      "lo": 0.8977180853334191,
      "hi": 0.9836792924637118,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9583333333333334,
      "lo": 0.8977180853334191,
      "hi": 0.9836792924637118,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8645833333333334,
      "lo": 0.7819886149785562,
      "hi": 0.9191229355418891,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9279112754158965,
      "lo": 0.8637193032808941,
      "hi": 0.9762897669199265,
      "n": 81,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9615244121423243,
      "hi": 1,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7857142857142857,
      "lo": 0.524107694133997,
      "hi": 0.9242861328730683,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.675,
      "hi": 0.96,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9545454545454546,
      "lo": 0.8333333333333334,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9059421741627975,
      "hi": 1,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.895730002457548,
      "hi": 1,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8157894736842105,
      "lo": 0.665811419288686,
      "hi": 0.9077823481477872,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9541284403669725,
      "lo": 0.8970875639970409,
      "hi": 0.980249551586618,
      "n": 109,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9642857142857143,
      "lo": 0.9117533615468005,
      "hi": 0.9860253876053231,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9553571428571429,
      "lo": 0.8997310311335255,
      "hi": 0.9807827420733651,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8482142857142857,
      "lo": 0.7703137583391775,
      "hi": 0.9030203035249151,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9171075837742504,
      "lo": 0.8534319798396113,
      "hi": 0.9664022574955908,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9668386529330562,
      "hi": 1,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8125,
      "lo": 0.5699111903802586,
      "hi": 0.9340840092857187,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9024390243902439,
      "lo": 0.8067775974025975,
      "hi": 0.987012987012987,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8241207763533425,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8421052631578947,
      "lo": 0.6243452472967093,
      "hi": 0.9447952836146585,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9420289855072463,
      "lo": 0.8602075664233835,
      "hi": 0.9772276111196287,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9565217391304348,
      "lo": 0.8797879725062087,
      "hi": 0.9851040961037877,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9565217391304348,
      "lo": 0.8797879725062087,
      "hi": 0.9851040961037877,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.855072463768116,
      "lo": 0.7533647839478652,
      "hi": 0.9193290471932429,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9090909090909091,
      "lo": 0.8090477174137576,
      "hi": 0.9784192001237719,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9472627418109483,
      "hi": 1,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9090909090909091,
      "lo": 0.6226415635484043,
      "hi": 0.9837678271141151,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9090909090909091,
      "lo": 0.6226415635484043,
      "hi": 0.9837678271141151,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8181818181818182,
      "lo": 0.523019438039156,
      "hi": 0.9486323102539149,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6363636363636364,
      "lo": 0.35380117450784887,
      "hi": 0.8483352890463243,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9166666666666666,
      "lo": 0.782608695652174,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9230769230769231,
      "lo": 0.7272727272727273,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.96,
      "lo": 0.8888701291759625,
      "hi": 0.9863039357398561,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8933333333333333,
      "lo": 0.8033863715352693,
      "hi": 0.9449508723782568,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9164785553047404,
      "lo": 0.8391272306023859,
      "hi": 0.9725211416490486,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7692307692307693,
      "lo": 0.5794844592105632,
      "hi": 0.8896615059421671,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8846153846153846,
      "lo": 0.7102409678828635,
      "hi": 0.9599675537638938,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6538461538461539,
      "lo": 0.46220571188810816,
      "hi": 0.8058776967705947,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.916201209134296,
      "hi": 0.9999999999999999,
      "n": 42,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8372093023255814,
      "lo": 0.7002759410625283,
      "hi": 0.91883372652938,
      "n": 43,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9380530973451328,
      "lo": 0.8776301597761643,
      "hi": 0.969671825317382,
      "n": 113,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9658119658119658,
      "lo": 0.9153821514157074,
      "hi": 0.9866261581805496,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9572649572649573,
      "lo": 0.9038475294928947,
      "hi": 0.9816101689181098,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8376068376068376,
      "lo": 0.7602472015785341,
      "hi": 0.8935019402389367,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9099836333878887,
      "lo": 0.846286701208981,
      "hi": 0.9586299358207332,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9682107543372667,
      "hi": 1,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8333333333333334,
      "lo": 0.5519691377470266,
      "hi": 0.9530348578161463,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9,
      "lo": 0.7647058823529411,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8668077490609515,
      "hi": 0.9999999999999999,
      "n": 25,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8064516129032258,
      "lo": 0.6371974218820453,
      "hi": 0.908129916384139,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9032258064516129,
      "lo": 0.7510006155660716,
      "hi": 0.9665353558368026,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7096774193548387,
      "lo": 0.5340767066925007,
      "hi": 0.8390419984369939,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8235294117647058,
      "lo": 0.65625,
      "hi": 0.954570707070707,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.96,
      "lo": 0.8888701291759625,
      "hi": 0.9863039357398561,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9466666666666667,
      "lo": 0.8707401284620144,
      "hi": 0.9790665722533456,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8933333333333333,
      "lo": 0.8033863715352693,
      "hi": 0.9449508723782568,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9164785553047404,
      "lo": 0.8366201066854302,
      "hi": 0.9729790057915058,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9512761575171942,
      "hi": 1,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9215686274509803,
      "lo": 0.8039054966248795,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8571428571428571,
      "lo": 0.6005862050302965,
      "hi": 0.9599060787285351,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9411764705882353,
      "lo": 0.7301796936242461,
      "hi": 0.9895395990150025,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.85,
      "lo": 0.6395811352592431,
      "hi": 0.9476312541037835,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9253731343283582,
      "lo": 0.8309859154929577,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9375,
      "lo": 0.8618985123272557,
      "hi": 0.973010624329158,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.95,
      "lo": 0.8783772379535698,
      "hi": 0.9803864454644556,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9375,
      "lo": 0.8618985123272557,
      "hi": 0.973010624329158,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.825,
      "lo": 0.7274245802116865,
      "hi": 0.8927936355902206,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.910025706940874,
      "lo": 0.8208047124083051,
      "hi": 0.9727080844285145,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9541818704644728,
      "hi": 0.9999999999999999,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9166666666666666,
      "lo": 0.646120088858883,
      "hi": 0.9851349055950829,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8947368421052632,
      "lo": 0.6860591728889099,
      "hi": 0.9706414397011299,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.85,
      "lo": 0.6395811352592431,
      "hi": 0.9476312541037835,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9038461538461539,
      "lo": 0.7884615384615384,
      "hi": 0.9827586206896551,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.95,
      "lo": 0.8629948352365147,
      "hi": 0.9828504978356043,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9333333333333333,
      "lo": 0.8407464268680283,
      "hi": 0.9737713012754938,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9333333333333333,
      "lo": 0.8407464268680283,
      "hi": 0.9737713012754938,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8666666666666667,
      "lo": 0.7583484032350039,
      "hi": 0.9308589051941303,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.910025706940874,
      "lo": 0.8216961240310078,
      "hi": 0.9702620900076276,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.93982814785791,
      "hi": 0.9999999999999998,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9230769230769231,
      "lo": 0.7142857142857143,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8,
      "lo": 0.49016247153664183,
      "hi": 0.9433178485456247,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.85,
      "lo": 0.7142063492063494,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9655172413793104,
      "lo": 0.8282447812067973,
      "hi": 0.9938867857072374,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.896551724137931,
      "lo": 0.736149189092262,
      "hi": 0.9641851086493229,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9655172413793104,
      "lo": 0.8282447812067973,
      "hi": 0.9938867857072374,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.896551724137931,
      "lo": 0.736149189092262,
      "hi": 0.9641851086493229,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9109947643979057,
      "lo": 0.748716577540107,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9259259259259259,
      "lo": 0.7663040731697686,
      "hi": 0.9794453459390113,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8888888888888888,
      "lo": 0.7194219918172017,
      "hi": 0.9614796517169016,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8148148148148148,
      "lo": 0.6330131638145156,
      "hi": 0.9181929285702346,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9186046511627907,
      "lo": 0.8210082435003171,
      "hi": 0.9811320754716981,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.8754449702581328,
      "hi": 0.9999999999999998,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.86890625,
      "lo": 0.7818671875,
      "hi": 0.93860546875,
      "n": 120,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.525,
      "lo": 0.375,
      "hi": 0.75,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.5,
      "hi": 0.825,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.575,
      "hi": 0.875,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.525,
      "lo": 0.3749736210669248,
      "hi": 0.670645298873211,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.375,
      "lo": 0.24222979167233266,
      "hi": 0.5296756086269889,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.26799202452413634,
      "hi": 0.7320079754758637,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.42857142857142855,
      "lo": 0.21380798904474121,
      "hi": 0.6740935542034926,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8699654775604143,
      "lo": 0.7805859225163023,
      "hi": 0.9443901035673187,
      "n": 112,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5151515151515151,
      "lo": 0.36363636363636365,
      "hi": 0.7272727272727273,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6666666666666666,
      "lo": 0.45454545454545453,
      "hi": 0.8181818181818182,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6666666666666666,
      "lo": 0.5151515151515151,
      "hi": 0.8787878787878788,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5151515151515151,
      "lo": 0.3521837544891414,
      "hi": 0.674959578918663,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.012658227848101266,
      "lo": 0.0022379938550498787,
      "hi": 0.06827571876965954,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.3939393939393939,
      "lo": 0.2468310743447709,
      "hi": 0.5631655918005977,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04637121165392266,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8927777777777778,
      "lo": 0.7827638888888889,
      "hi": 0.9850416666666665,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5333333333333333,
      "lo": 0.26666666666666666,
      "hi": 0.8666666666666667,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7333333333333333,
      "lo": 0.4666666666666667,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7333333333333333,
      "lo": 0.5333333333333333,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5333333333333333,
      "lo": 0.30116980025498397,
      "hi": 0.7519046463426261,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.4,
      "lo": 0.1982449614134158,
      "hi": 0.6425316987937539,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8090277777777778,
      "lo": 0.5833333333333334,
      "hi": 0.9826388888888888,
      "n": 26,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.887668918918919,
      "lo": 0.8105954391891892,
      "hi": 0.9525422297297297,
      "n": 117,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5405405405405406,
      "lo": 0.3783783783783784,
      "hi": 0.7567567567567568,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7297297297297297,
      "lo": 0.5405405405405406,
      "hi": 0.8648648648648649,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7297297297297297,
      "lo": 0.5945945945945946,
      "hi": 0.918918918918919,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5405405405405406,
      "lo": 0.3838404689217949,
      "hi": 0.6896143019562697,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.40540540540540543,
      "lo": 0.26346518192014284,
      "hi": 0.5651403526977063,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9166666666666666,
      "lo": 0.646120088858883,
      "hi": 0.9851349055950829,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8333333333333334,
      "lo": 0.5519691377470266,
      "hi": 0.9530348578161463,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8596491228070176,
      "lo": 0.6907894736842105,
      "hi": 0.9912280701754386,
      "n": 31,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6666666666666666,
      "lo": 0.4166666666666667,
      "hi": 0.9166666666666666,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6666666666666666,
      "lo": 0.4166666666666667,
      "hi": 0.9166666666666666,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6666666666666666,
      "lo": 0.4166666666666667,
      "hi": 0.9166666666666666,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5833333333333334,
      "lo": 0.31951131254954973,
      "hi": 0.8067396863412435,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.3333333333333333,
      "lo": 0.13812009109121315,
      "hi": 0.6093779111272004,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.8927777777777778,
      "lo": 0.7688611111111111,
      "hi": 0.977236111111111,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5333333333333333,
      "lo": 0.26666666666666666,
      "hi": 0.8666666666666667,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7333333333333333,
      "lo": 0.4666666666666667,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7333333333333333,
      "lo": 0.5333333333333333,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5333333333333333,
      "lo": 0.30116980025498397,
      "hi": 0.7519046463426261,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.4,
      "lo": 0.1982449614134158,
      "hi": 0.6425316987937539,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.3,
      "lo": 0.10779126740630099,
      "hi": 0.6032218525388546,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.1,
      "lo": 0.017876213095072896,
      "hi": 0.4041500267952385,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.016666666666666666,
      "lo": 0.0029481597947862495,
      "hi": 0.08855129727590061,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0.4,
      "lo": 0.16818032970623614,
      "hi": 0.6873262302663417,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.1,
      "lo": 0.017876213095072896,
      "hi": 0.4041500267952385,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.037037037037037035,
      "lo": 0.006568145980785103,
      "hi": 0.18283465933575843,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.2992980081982123,
      "hi": 0.7007019918017877,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.4,
      "lo": 0.21880653237281705,
      "hi": 0.6134184992377469,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.55,
      "lo": 0.34208534245034233,
      "hi": 0.7418021417443759,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.35,
      "lo": 0.18119182410108206,
      "hi": 0.5671457233147638,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.87125,
      "lo": 0.7459296875,
      "hi": 0.9728125,
      "n": 100,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.3,
      "hi": 0.75,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4,
      "hi": 0.9,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.5,
      "hi": 0.95,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.2992980081982123,
      "hi": 0.7007019918017877,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.25,
      "lo": 0.11186170140766569,
      "hi": 0.468700877618744,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.82125,
      "lo": 0.6237343750000001,
      "hi": 0.9704999999999973,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6,
      "lo": 0.3,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.911875,
      "lo": 0.8087031250000001,
      "hi": 0.993140625,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.2,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7990384615384616,
      "lo": 0.6858112980769231,
      "hi": 0.8997716346153846,
      "n": 106,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.3076923076923077,
      "lo": 0.15384615384615385,
      "hi": 0.5769230769230769,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5384615384615384,
      "lo": 0.3076923076923077,
      "hi": 0.7307692307692307,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.5384615384615384,
      "lo": 0.34615384615384615,
      "hi": 0.8076923076923077,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.3076923076923077,
      "lo": 0.16501315595463767,
      "hi": 0.4998825832219837,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.15384615384615385,
      "lo": 0.06150033723578355,
      "hi": 0.3353119932821348,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9986607142857142,
      "lo": 0.9933035714285714,
      "hi": 1,
      "n": 94,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9285714285714286,
      "lo": 0.7857142857142857,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 0.9285714285714286,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.7857142857142857,
      "lo": 0.524107694133997,
      "hi": 0.9242861328730683,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 7253.5,
      "lo": 7253.5,
      "hi": 7253.5,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 11792.649999999994,
      "lo": 11792.649999999994,
      "hi": 11792.649999999994,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 14391.14,
      "lo": 14391.14,
      "hi": 14391.14,
      "n": 150,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010091608333333336,
      "lo": 0.0010091608333333336,
      "hi": 0.0010091608333333336,
      "n": 150,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010091608333333336,
      "lo": 0.0010091608333333336,
      "hi": 0.0010091608333333336,
      "n": 150,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "all",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 7159.5,
      "lo": 7159.5,
      "hi": 7159.5,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 11865.25,
      "lo": 11865.25,
      "hi": 11865.25,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 14394.5,
      "lo": 14394.5,
      "hi": 14394.5,
      "n": 126,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009943869841269842,
      "lo": 0.0009943869841269842,
      "hi": 0.0009943869841269842,
      "n": 126,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009943869841269842,
      "lo": 0.0009943869841269842,
      "hi": 0.0009943869841269842,
      "n": 126,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 8849,
      "lo": 8849,
      "hi": 8849,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 12099.15,
      "lo": 12099.15,
      "hi": 12099.15,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 13091.829999999998,
      "lo": 13091.829999999998,
      "hi": 13091.829999999998,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0011613314285714284,
      "lo": 0.0011613314285714284,
      "hi": 0.0011613314285714284,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0011613314285714284,
      "lo": 0.0011613314285714284,
      "hi": 0.0011613314285714284,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 7721.5,
      "lo": 7721.5,
      "hi": 7721.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 9714.099999999999,
      "lo": 9714.099999999999,
      "hi": 9714.099999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 10038.82,
      "lo": 10038.82,
      "hi": 10038.82,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009822725,
      "lo": 0.0009822725,
      "hi": 0.0009822725,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009822725,
      "lo": 0.0009822725,
      "hi": 0.0009822725,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 6832,
      "lo": 6832,
      "hi": 6832,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 10236.249999999998,
      "lo": 10236.249999999998,
      "hi": 10236.249999999998,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 12719.249999999996,
      "lo": 12719.249999999996,
      "hi": 12719.249999999996,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009613939285714284,
      "lo": 0.0009613939285714284,
      "hi": 0.0009613939285714284,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009613939285714284,
      "lo": 0.0009613939285714284,
      "hi": 0.0009613939285714284,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "base=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 7061.5,
      "lo": 7061.5,
      "hi": 7061.5,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 11562.25,
      "lo": 11562.25,
      "hi": 11562.25,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 14393.1,
      "lo": 14393.1,
      "hi": 14393.1,
      "n": 136,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009958804044117647,
      "lo": 0.0009958804044117647,
      "hi": 0.0009958804044117647,
      "n": 136,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009958804044117647,
      "lo": 0.0009958804044117647,
      "hi": 0.0009958804044117647,
      "n": 136,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "capture=photo",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 8751.5,
      "lo": 8751.5,
      "hi": 8751.5,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 12052.600000000002,
      "lo": 12052.600000000002,
      "hi": 12052.600000000002,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 13520.919999999998,
      "lo": 13520.919999999998,
      "hi": 13520.919999999998,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012388225,
      "lo": 0.0012388225,
      "hi": 0.0012388225,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012388225,
      "lo": 0.0012388225,
      "hi": 0.0012388225,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_full",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 7513,
      "lo": 7513,
      "hi": 7513,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 10914.849999999999,
      "lo": 10914.849999999999,
      "hi": 10914.849999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 11327.77,
      "lo": 11327.77,
      "hi": 11327.77,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.00103786,
      "lo": 0.00103786,
      "hi": 0.00103786,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0.00103786,
      "lo": 0.00103786,
      "hi": 0.00103786,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 7744,
      "lo": 7744,
      "hi": 7744,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 9900.249999999998,
      "lo": 9900.249999999998,
      "hi": 9900.249999999998,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 10383.630000000001,
      "lo": 10383.630000000001,
      "hi": 10383.630000000001,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010235058333333334,
      "lo": 0.0010235058333333334,
      "hi": 0.0010235058333333334,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010235058333333334,
      "lo": 0.0010235058333333334,
      "hi": 0.0010235058333333334,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=duplicate",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 6948,
      "lo": 6948,
      "hi": 6948,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 13278.8,
      "lo": 13278.8,
      "hi": 13278.8,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 15901.999999999967,
      "lo": 15901.999999999967,
      "hi": 15901.999999999967,
      "n": 69,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009681042028985504,
      "lo": 0.0009681042028985504,
      "hi": 0.0009681042028985504,
      "n": 69,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009681042028985504,
      "lo": 0.0009681042028985504,
      "hi": 0.0009681042028985504,
      "n": 69,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=genuine",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 6140,
      "lo": 6140,
      "hi": 6140,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 8160.5,
      "lo": 8160.5,
      "hi": 8160.5,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 8504.1,
      "lo": 8504.1,
      "hi": 8504.1,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0008001918181818182,
      "lo": 0.0008001918181818182,
      "hi": 0.0008001918181818182,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0008001918181818182,
      "lo": 0.0008001918181818182,
      "hi": 0.0008001918181818182,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=hard_negative",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 6699,
      "lo": 6699,
      "hi": 6699,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 11191.249999999995,
      "lo": 11191.249999999995,
      "hi": 11191.249999999995,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 12910.25,
      "lo": 12910.25,
      "hi": 12910.25,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009912599999999997,
      "lo": 0.0009912599999999997,
      "hi": 0.0009912599999999997,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009912599999999997,
      "lo": 0.0009912599999999997,
      "hi": 0.0009912599999999997,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=manual_edit",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 6869,
      "lo": 6869,
      "hi": 6869,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 10150.5,
      "lo": 10150.5,
      "hi": 10150.5,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 14855.399999999972,
      "lo": 14855.399999999972,
      "hi": 14855.399999999972,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009537091758241758,
      "lo": 0.0009537091758241758,
      "hi": 0.0009537091758241758,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009537091758241758,
      "lo": 0.0009537091758241758,
      "hi": 0.0009537091758241758,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=IDR",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 7514.5,
      "lo": 7514.5,
      "hi": 7514.5,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 10505.699999999997,
      "lo": 10505.699999999997,
      "hi": 10505.699999999997,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 12502.16,
      "lo": 12502.16,
      "hi": 12502.16,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010036006249999996,
      "lo": 0.0010036006249999996,
      "hi": 0.0010036006249999996,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010036006249999996,
      "lo": 0.0010036006249999996,
      "hi": 0.0010036006249999996,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=USD",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 7223,
      "lo": 7223,
      "hi": 7223,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 11847.099999999997,
      "lo": 11847.099999999997,
      "hi": 11847.099999999997,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 14391.56,
      "lo": 14391.56,
      "hi": 14391.56,
      "n": 147,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010068637414965987,
      "lo": 0.0010068637414965987,
      "hi": 0.0010068637414965987,
      "n": 147,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010068637414965987,
      "lo": 0.0010068637414965987,
      "hi": 0.0010068637414965987,
      "n": 147,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "docType=receipt",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 8469.5,
      "lo": 8469.5,
      "hi": 8469.5,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 12290.05,
      "lo": 12290.05,
      "hi": 12290.05,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 13130.010000000002,
      "lo": 13130.010000000002,
      "hi": 13130.010000000002,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001133280833333333,
      "lo": 0.001133280833333333,
      "hi": 0.001133280833333333,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001133280833333333,
      "lo": 0.001133280833333333,
      "hi": 0.001133280833333333,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "editedField=total",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 7949,
      "lo": 7949,
      "hi": 7949,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 11236.199999999997,
      "lo": 11236.199999999997,
      "hi": 11236.199999999997,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 13865.160000000003,
      "lo": 13865.160000000003,
      "hi": 13865.160000000003,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001039915555555555,
      "lo": 0.001039915555555555,
      "hi": 0.001039915555555555,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001039915555555555,
      "lo": 0.001039915555555555,
      "hi": 0.001039915555555555,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=en",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 6869,
      "lo": 6869,
      "hi": 6869,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 10150.5,
      "lo": 10150.5,
      "hi": 10150.5,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 14855.399999999972,
      "lo": 14855.399999999972,
      "hi": 14855.399999999972,
      "n": 91,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009537091758241758,
      "lo": 0.0009537091758241758,
      "hi": 0.0009537091758241758,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009537091758241758,
      "lo": 0.0009537091758241758,
      "hi": 0.0009537091758241758,
      "n": 91,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=id",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 8103,
      "lo": 8103,
      "hi": 8103,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 11792.65,
      "lo": 11792.65,
      "hi": 11792.65,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 11923.33,
      "lo": 11923.33,
      "hi": 11923.33,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012096475,
      "lo": 0.0012096475,
      "hi": 0.0012096475,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012096475,
      "lo": 0.0012096475,
      "hi": 0.0012096475,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 9244.5,
      "lo": 9244.5,
      "hi": 9244.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 12667.599999999997,
      "lo": 12667.599999999997,
      "hi": 12667.599999999997,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 13643.92,
      "lo": 13643.92,
      "hi": 13643.92,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012679974999999998,
      "lo": 0.0012679974999999998,
      "hi": 0.0012679974999999998,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0012679974999999998,
      "lo": 0.0012679974999999998,
      "hi": 0.0012679974999999998,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=free",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 7543,
      "lo": 7543,
      "hi": 7543,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 11611.15,
      "lo": 11611.15,
      "hi": 11611.15,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 11887.029999999999,
      "lo": 11887.029999999999,
      "hi": 11887.029999999999,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010767724999999997,
      "lo": 0.0010767724999999997,
      "hi": 0.0010767724999999997,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010767724999999997,
      "lo": 0.0010767724999999997,
      "hi": 0.0010767724999999997,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=intact",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 7007,
      "lo": 7007,
      "hi": 7007,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 10343.15,
      "lo": 10343.15,
      "hi": 10343.15,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 14396.74,
      "lo": 14396.74,
      "hi": 14396.74,
      "n": 110,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009664224999999999,
      "lo": 0.0009664224999999999,
      "hi": 0.0009664224999999999,
      "n": 110,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009664224999999999,
      "lo": 0.0009664224999999999,
      "hi": 0.0009664224999999999,
      "n": 110,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 8068.5,
      "lo": 8068.5,
      "hi": 8068.5,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 13367.4,
      "lo": 13367.4,
      "hi": 13367.4,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 13783.88,
      "lo": 13783.88,
      "hi": 13783.88,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0011766100000000002,
      "lo": 0.0011766100000000002,
      "hi": 0.0011766100000000002,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0011766100000000002,
      "lo": 0.0011766100000000002,
      "hi": 0.0011766100000000002,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=stripped",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 6873,
      "lo": 6873,
      "hi": 6873,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 10135.25,
      "lo": 10135.25,
      "hi": 10135.25,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 15562.5,
      "lo": 15562.5,
      "hi": 15562.5,
      "n": 76,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.000948151447368421,
      "lo": 0.000948151447368421,
      "hi": 0.000948151447368421,
      "n": 76,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0.000948151447368421,
      "lo": 0.000948151447368421,
      "hi": 0.000948151447368421,
      "n": 76,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=cord",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 6699,
      "lo": 6699,
      "hi": 6699,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 11191.249999999995,
      "lo": 11191.249999999995,
      "hi": 11191.249999999995,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 12910.25,
      "lo": 12910.25,
      "hi": 12910.25,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009912599999999997,
      "lo": 0.0009912599999999997,
      "hi": 0.0009912599999999997,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0009912599999999997,
      "lo": 0.0009912599999999997,
      "hi": 0.0009912599999999997,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 7847,
      "lo": 7847,
      "hi": 7847,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 11412.499999999995,
      "lo": 11412.499999999995,
      "hi": 11412.499999999995,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 13998.370000000003,
      "lo": 13998.370000000003,
      "hi": 13998.370000000003,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010072636764705879,
      "lo": 0.0010072636764705879,
      "hi": 0.0010072636764705879,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010072636764705879,
      "lo": 0.0010072636764705879,
      "hi": 0.0010072636764705879,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=expressexpense",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 9723.5,
      "lo": 9723.5,
      "hi": 9723.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 13018.599999999999,
      "lo": 13018.599999999999,
      "hi": 13018.599999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 13714.12,
      "lo": 13714.12,
      "hi": 13714.12,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0.00130631,
      "lo": 0.00130631,
      "hi": 0.00130631,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0.00130631,
      "lo": 0.00130631,
      "hi": 0.00130631,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 7801.5,
      "lo": 7801.5,
      "hi": 7801.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 10143.599999999999,
      "lo": 10143.599999999999,
      "hi": 10143.599999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 10659.12,
      "lo": 10659.12,
      "hi": 10659.12,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001171335,
      "lo": 0.001171335,
      "hi": 0.001171335,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0.001171335,
      "lo": 0.001171335,
      "hi": 0.001171335,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 7377,
      "lo": 7377,
      "hi": 7377,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 10496.900000000005,
      "lo": 10496.900000000005,
      "hi": 10496.900000000005,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 16909.959999999985,
      "lo": 16909.959999999985,
      "hi": 16909.959999999985,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010409491025641028,
      "lo": 0.0010409491025641028,
      "hi": 0.0010409491025641028,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0010409491025641028,
      "lo": 0.0010409491025641028,
      "hi": 0.0010409491025641028,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 6371,
      "lo": 6371,
      "hi": 6371,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 8362.8,
      "lo": 8362.8,
      "hi": 8362.8,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 12659.199999999999,
      "lo": 12659.199999999999,
      "hi": 12659.199999999999,
      "n": 33,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0008338433333333333,
      "lo": 0.0008338433333333333,
      "hi": 0.0008338433333333333,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0.0008338433333333333,
      "lo": 0.0008338433333333333,
      "hi": 0.0008338433333333333,
      "n": 33,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=none",
      "target": "diy:claude-haiku-5.5",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9777777777777777,
      "lo": 0.8843331823158513,
      "hi": 0.9960664011171667,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.9123783988027135,
      "hi": 1,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.9229264369144198,
      "hi": 1,
      "n": 46,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9224137931034483,
      "lo": 0.8591003375006443,
      "hi": 0.9586467173531092,
      "n": 116,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9833333333333333,
      "lo": 0.941264037027841,
      "hi": 0.9954174354340789,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9833333333333333,
      "lo": 0.941264037027841,
      "hi": 0.9954174354340789,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8620237953250198,
      "hi": 1,
      "n": 24,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9083333333333333,
      "lo": 0.843291530273291,
      "hi": 0.9480428171514347,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9408,
      "lo": 0.8881567445712183,
      "hi": 0.9806007851169141,
      "n": 98,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9916666666666667,
      "lo": 0.9543037087549505,
      "hi": 0.998527444266658,
      "n": 120,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9705882352941176,
      "lo": 0.8508442670731406,
      "hi": 0.9947890937237309,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8864866068260312,
      "hi": 0.9999999999999999,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8984854458466761,
      "hi": 0.9999999999999999,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.967391304347826,
      "lo": 0.9084664004700642,
      "hi": 0.9888488225890284,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9791666666666666,
      "lo": 0.9271928648221579,
      "hi": 0.9942680301475697,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9895833333333334,
      "lo": 0.9433338237728424,
      "hi": 0.9981588297831838,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9479166666666666,
      "lo": 0.8838152196850738,
      "hi": 0.9775503995257587,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9573283858998145,
      "lo": 0.9157088122605364,
      "hi": 0.9854484919702311,
      "n": 81,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9895833333333334,
      "lo": 0.9433338237728424,
      "hi": 0.9981588297831838,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7666666666666667,
      "lo": 0.5116279069767442,
      "hi": 1,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0.5,
      "lo": 0.236593090512564,
      "hi": 0.7634069094874361,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9285714285714286,
      "lo": 0.6853129557584889,
      "hi": 0.9872777847521093,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.972972972972973,
      "lo": 0.861759301362695,
      "hi": 0.9952130255480596,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.895730002457548,
      "hi": 1,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9357798165137615,
      "lo": 0.8733427976315921,
      "hi": 0.9685463536860605,
      "n": 109,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9821428571428571,
      "lo": 0.9372195125788385,
      "hi": 0.9950891884637512,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9821428571428571,
      "lo": 0.9372195125788385,
      "hi": 0.9950891884637512,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9196428571428571,
      "lo": 0.8543044472628575,
      "hi": 0.9571494221631002,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.95929203539823,
      "lo": 0.9248456148376096,
      "hi": 0.9874627681910957,
      "n": 92,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9910714285714286,
      "lo": 0.9511515316911152,
      "hi": 0.9984221452967079,
      "n": 112,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0.875,
      "lo": 0.639771727342413,
      "hi": 0.9650225122567595,
      "n": 16,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8658536585365854,
      "lo": 0.7124585843373495,
      "hi": 0.9782608695652174,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9444444444444444,
      "lo": 0.7424269921812741,
      "hi": 0.990124809021697,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8318207759473837,
      "hi": 1,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.927536231884058,
      "lo": 0.8413260579060098,
      "hi": 0.9686522285700185,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9710144927536232,
      "lo": 0.9003341623693445,
      "hi": 0.9920147973076358,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9710144927536232,
      "lo": 0.9003341623693445,
      "hi": 0.9920147973076358,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8985507246376812,
      "lo": 0.8050811424505202,
      "hi": 0.9499833618915401,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9616519174041298,
      "lo": 0.9125431186546981,
      "hi": 0.9948986066507822,
      "n": 50,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9855072463768116,
      "lo": 0.9223687753885529,
      "hi": 0.9974370753554117,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9090909090909091,
      "lo": 0.6226415635484043,
      "hi": 0.9837678271141151,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9090909090909091,
      "lo": 0.6226415635484043,
      "hi": 0.9837678271141151,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9733333333333334,
      "lo": 0.9078851181224086,
      "hi": 0.9926563109938686,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9733333333333334,
      "lo": 0.9078851181224086,
      "hi": 0.9926563109938686,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.96,
      "lo": 0.8888701291759625,
      "hi": 0.9863039357398561,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9705215419501134,
      "lo": 0.9333256351039261,
      "hi": 0.9957446808510638,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7692307692307693,
      "lo": 0.5794844592105632,
      "hi": 0.8896615059421671,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9615384615384616,
      "lo": 0.8110722109696524,
      "hi": 0.9931780150064564,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7307692307692307,
      "lo": 0.5391695962082381,
      "hi": 0.8629555167798162,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8712710781407846,
      "hi": 1,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9761904761904762,
      "lo": 0.8767879842623334,
      "hi": 0.9957845958655673,
      "n": 42,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.908190131774416,
      "hi": 0.9999999999999999,
      "n": 38,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.9179901967742088,
      "hi": 1,
      "n": 43,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9292035398230089,
      "lo": 0.8664924814187024,
      "hi": 0.9636922918547725,
      "n": 113,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9829059829059829,
      "lo": 0.9398099145713432,
      "hi": 0.9952996173954185,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9829059829059829,
      "lo": 0.9398099145713432,
      "hi": 0.9952996173954185,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8453609810751531,
      "hi": 1,
      "n": 21,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9145299145299145,
      "lo": 0.8497921257293599,
      "hi": 0.9529125167553825,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9392446633825944,
      "lo": 0.8868515228570455,
      "hi": 0.9804000378286362,
      "n": 96,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9914529914529915,
      "lo": 0.9531704967258107,
      "hi": 0.9984896464262035,
      "n": 117,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0.95,
      "lo": 0.8571428571428571,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8668077490609515,
      "hi": 0.9999999999999999,
      "n": 25,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8064516129032258,
      "lo": 0.6371974218820453,
      "hi": 0.908129916384139,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.967741935483871,
      "lo": 0.838058948352751,
      "hi": 0.9942827784745831,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7741935483870968,
      "lo": 0.6018758161665794,
      "hi": 0.886048644387375,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8529411764705882,
      "lo": 0.6896012931034484,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.889744604539564,
      "hi": 1,
      "n": 31,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9733333333333334,
      "lo": 0.9078851181224086,
      "hi": 0.9926563109938686,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9733333333333334,
      "lo": 0.9078851181224086,
      "hi": 0.9926563109938686,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.96,
      "lo": 0.8888701291759625,
      "hi": 0.9863039357398561,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9705215419501134,
      "lo": 0.931816844919786,
      "hi": 0.995850622406639,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9866666666666667,
      "lo": 0.9282663444557845,
      "hi": 0.9976424488609515,
      "n": 75,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8823529411764706,
      "lo": 0.660377358490566,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9411764705882353,
      "lo": 0.7301796936242461,
      "hi": 0.9895395990150025,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7719046276458016,
      "hi": 0.9999999999999999,
      "n": 13,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8656716417910447,
      "lo": 0.6891816816816817,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9473684210526315,
      "lo": 0.753612688331012,
      "hi": 0.9906480059376995,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.925,
      "lo": 0.8458798391878072,
      "hi": 0.9651747507069949,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.975,
      "lo": 0.9133556701442198,
      "hi": 0.9931171067970292,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.975,
      "lo": 0.9133556701442198,
      "hi": 0.9931171067970292,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.8148931119389591,
      "hi": 0.9484523844326191,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9664082687338501,
      "lo": 0.9234965707594514,
      "hi": 0.9949748743718593,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9875,
      "lo": 0.9325372992233133,
      "hi": 0.9977900244795476,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8947368421052632,
      "lo": 0.6860591728889099,
      "hi": 0.9706414397011299,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7411670330319684,
      "hi": 1,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.6989663547715128,
      "hi": 0.9721335187862319,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9423076923076923,
      "lo": 0.8371974371143807,
      "hi": 1,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9833333333333333,
      "lo": 0.9114487027240993,
      "hi": 0.9970518402052136,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9666666666666667,
      "lo": 0.886362257256914,
      "hi": 0.9908106807438021,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9833333333333333,
      "lo": 0.9114487027240993,
      "hi": 0.9970518402052136,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9666666666666667,
      "lo": 0.886362257256914,
      "hi": 0.9908106807438021,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9664082687338501,
      "lo": 0.9211114050336332,
      "hi": 0.9950986370157819,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9833333333333333,
      "lo": 0.9114487027240993,
      "hi": 0.9970518402052136,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9473684210526315,
      "lo": 0.753612688331012,
      "hi": 0.9906480059376995,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8156818649911483,
      "hi": 1,
      "n": 17,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.75,
      "lo": 0.531299122381256,
      "hi": 0.8881382985923343,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.95,
      "lo": 0.763868806553258,
      "hi": 0.9911185511992047,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4810271816464765,
      "hi": 0.8545227551323956,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.merchant",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.date",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.currency",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.receipt_number",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9,
      "lo": 0.5958499732047615,
      "hi": 0.9821237869049271,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8,
      "lo": 0.5555555555555556,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9895833333333334,
      "lo": 0.9680851063829787,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8830302015002593,
      "hi": 1,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.subtotal",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.tax",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9259259259259259,
      "lo": 0.7663040731697686,
      "hi": 0.9794453459390113,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "field_accuracy.total",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "all_key_fields",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9259259259259259,
      "lo": 0.7663040731697686,
      "hi": 0.9794453459390113,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "line_items_f1",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9349112426035503,
      "lo": 0.8296205962059621,
      "hi": 1,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "extraction",
      "metric": "valid_json",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9629629629629629,
      "lo": 0.8171653406642414,
      "hi": 0.9934318540192149,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.9065625,
      "lo": 0.825296875,
      "hi": 0.9715703124999999,
      "n": 120,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.825,
      "lo": 0.7,
      "hi": 0.95,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.85,
      "lo": 0.725,
      "hi": 0.95,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.85,
      "lo": 0.725,
      "hi": 0.95,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.825,
      "lo": 0.6805000966821229,
      "hi": 0.9125458625396408,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.825,
      "lo": 0.6805000966821229,
      "hi": 0.9125458625396408,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6428571428571429,
      "lo": 0.38764423103907397,
      "hi": 0.8365526824644587,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.887993862677407,
      "lo": 0.7997171077867281,
      "hi": 0.9666283084004603,
      "n": 112,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7878787878787878,
      "lo": 0.6363636363636364,
      "hi": 0.9393939393939394,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8181818181818182,
      "lo": 0.6666666666666666,
      "hi": 0.9393939393939394,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8181818181818182,
      "lo": 0.6666666666666666,
      "hi": 0.9393939393939394,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7878787878787878,
      "lo": 0.6224835500784931,
      "hi": 0.8932397846697919,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04637121165392266,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7878787878787878,
      "lo": 0.6224835500784931,
      "hi": 0.8932397846697919,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04637121165392266,
      "n": 79,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8411111111111111,
      "lo": 0.703875,
      "hi": 0.96,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.4666666666666667,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7333333333333333,
      "lo": 0.4666666666666667,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7333333333333333,
      "lo": 0.4666666666666667,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.41713547738519774,
      "hi": 0.8482367556028526,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.41713547738519774,
      "hi": 0.8482367556028526,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8368055555555556,
      "lo": 0.5867187500000002,
      "hi": 1,
      "n": 26,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.05555555555555555,
      "lo": 0.009875190978303097,
      "hi": 0.25757300781872594,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.17587922364665765,
      "n": 18,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8989864864864865,
      "lo": 0.8178927364864864,
      "hi": 0.9695945945945946,
      "n": 117,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8108108108108109,
      "lo": 0.6756756756756757,
      "hi": 0.918918918918919,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8378378378378378,
      "lo": 0.7027027027027027,
      "hi": 0.9459459459459459,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8378378378378378,
      "lo": 0.7297297297297297,
      "hi": 0.9459459459459459,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8108108108108109,
      "lo": 0.6579530307016159,
      "hi": 0.9052002126968799,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8108108108108109,
      "lo": 0.6579530307016159,
      "hi": 0.9052002126968799,
      "n": 37,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7575059933447592,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8947368421052632,
      "lo": 0.7302083333333335,
      "hi": 1,
      "n": 31,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8333333333333334,
      "lo": 0.5833333333333334,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8333333333333334,
      "lo": 0.5833333333333334,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8333333333333334,
      "lo": 0.5833333333333334,
      "hi": 1,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8333333333333334,
      "lo": 0.5519691377470266,
      "hi": 0.9530348578161463,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.05263157894736842,
      "lo": 0.009351994062300362,
      "hi": 0.24638731166898786,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8333333333333334,
      "lo": 0.5519691377470266,
      "hi": 0.9530348578161463,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16817922405261626,
      "n": 19,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8411111111111111,
      "lo": 0.7022222222222222,
      "hi": 0.9605555555555556,
      "n": 75,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.46500000000000297,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7333333333333333,
      "lo": 0.5333333333333333,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7333333333333333,
      "lo": 0.5333333333333333,
      "hi": 0.9333333333333333,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.41713547738519774,
      "hi": 0.8482367556028526,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6666666666666666,
      "lo": 0.41713547738519774,
      "hi": 0.8482367556028526,
      "n": 15,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.06017185214208986,
      "n": 60,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.05,
      "lo": 0.008881448800795402,
      "hi": 0.23613119344674205,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7224672001371107,
      "hi": 0.9999999999999999,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.11696979849974075,
      "n": 29,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.12455502974186705,
      "n": 27,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8,
      "lo": 0.5839825677481064,
      "hi": 0.919342337420202,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.85,
      "lo": 0.6395811352592431,
      "hi": 0.9476312541037835,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.85,
      "lo": 0.6395811352592431,
      "hi": 0.9476312541037835,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_5",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0125,
      "lo": 0.0022099755204522745,
      "hi": 0.06746270077668665,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "false_flag_rate_at_risk_0_7",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.0458181295355271,
      "n": 80,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 100,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.8388748419471806,
      "hi": 1,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.79375,
      "lo": 0.5555937500000001,
      "hi": 1,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.39677814746114537,
      "hi": 0.8922087325936989,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.8325,
      "lo": 0.6625,
      "hi": 0.951265625,
      "n": 90,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6,
      "lo": 0.3,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4,
      "hi": 0.9,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7,
      "lo": 0.4,
      "hi": 1,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.6,
      "lo": 0.31267376973365824,
      "hi": 0.8318196702937638,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.85625,
      "lo": 0.7463882211538462,
      "hi": 0.9567307692307693,
      "n": 106,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7307692307692307,
      "lo": 0.5384615384615384,
      "hi": 0.8846153846153846,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7692307692307693,
      "lo": 0.5769230769230769,
      "hi": 0.9230769230769231,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7692307692307693,
      "lo": 0.5769230769230769,
      "hi": 0.9230769230769231,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7307692307692307,
      "lo": 0.5391695962082381,
      "hi": 0.8629555167798162,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.7307692307692307,
      "lo": 0.5391695962082381,
      "hi": 0.8629555167798162,
      "n": 26,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "auc",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 94,
      "unit": "auc",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_1",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_5",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_fpr_10",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 1,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_5",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "authenticity",
      "metric": "detection_at_risk_0_7",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 1,
      "lo": 0.7846891972623643,
      "hi": 1,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": true
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 7251,
      "lo": 7251,
      "hi": 7251,
      "n": 149,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 54213.399999999994,
      "lo": 54213.399999999994,
      "hi": 54213.399999999994,
      "n": 149,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 99639.56000000016,
      "lo": 99639.56000000016,
      "hi": 99639.56000000016,
      "n": 149,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004288223154362417,
      "lo": 0.004288223154362417,
      "hi": 0.004288223154362417,
      "n": 149,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004288223154362417,
      "lo": 0.004288223154362417,
      "hi": 0.004288223154362417,
      "n": 149,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.0249702443680766,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "all",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006666666666666667,
      "lo": 0.0011778013350174366,
      "hi": 0.03679283977481815,
      "n": 150,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 7221,
      "lo": 7221,
      "hi": 7221,
      "n": 125,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 54460.2,
      "lo": 54460.2,
      "hi": 54460.2,
      "n": 125,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 103390.28000000009,
      "lo": 103390.28000000009,
      "hi": 103390.28000000009,
      "n": 125,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004098516,
      "lo": 0.004098516,
      "hi": 0.004098516,
      "n": 125,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004098516,
      "lo": 0.004098516,
      "hi": 0.004098516,
      "n": 125,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.734723475976807e-18,
      "hi": 0.02958576448219845,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=consistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.007936507936507936,
      "lo": 0.0014023650608123127,
      "hi": 0.04358679998516077,
      "n": 126,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 10114.5,
      "lo": 10114.5,
      "hi": 10114.5,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 35130.09999999999,
      "lo": 35130.09999999999,
      "hi": 35130.09999999999,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 53530.81999999997,
      "lo": 53530.81999999997,
      "hi": 53530.81999999997,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006461196428571429,
      "lo": 0.006461196428571429,
      "hi": 0.006461196428571429,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006461196428571429,
      "lo": 0.006461196428571429,
      "hi": 0.006461196428571429,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=inconsistent",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 6751,
      "lo": 6751,
      "hi": 6751,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 24032.599999999977,
      "lo": 24032.599999999977,
      "hi": 24032.599999999977,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 32784.92,
      "lo": 32784.92,
      "hi": 32784.92,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0036173999999999998,
      "lo": 0.0036173999999999998,
      "hi": 0.0036173999999999998,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0036173999999999998,
      "lo": 0.0036173999999999998,
      "hi": 0.0036173999999999998,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "arithmetic=unknown",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 8990,
      "lo": 8990,
      "hi": 8990,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 24522.45,
      "lo": 24522.45,
      "hi": 24522.45,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 25181.29,
      "lo": 25181.29,
      "hi": 25181.29,
      "n": 14,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005539178571428572,
      "lo": 0.005539178571428572,
      "hi": 0.005539178571428572,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005539178571428572,
      "lo": 0.005539178571428572,
      "hi": 0.005539178571428572,
      "n": 14,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "base=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 1.3877787807814457e-17,
      "hi": 0.2153108027376358,
      "n": 14,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 7221,
      "lo": 7221,
      "hi": 7221,
      "n": 135,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 55734.19999999999,
      "lo": 55734.19999999999,
      "hi": 55734.19999999999,
      "n": 135,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 101827.47999999995,
      "lo": 101827.47999999995,
      "hi": 101827.47999999995,
      "n": 135,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0041782611111111125,
      "lo": 0.0041782611111111125,
      "hi": 0.0041782611111111125,
      "n": 135,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0041782611111111125,
      "lo": 0.0041782611111111125,
      "hi": 0.0041782611111111125,
      "n": 135,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.027470099733582408,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "capture=photo",
      "target": "diy:gemini-3.8-flash",
      "value": 0.007352941176470588,
      "lo": 0.001299156036095813,
      "hi": 0.04047285399552214,
      "n": 136,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 10731.5,
      "lo": 10731.5,
      "hi": 10731.5,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 45587.95000000002,
      "lo": 45587.95000000002,
      "hi": 45587.95000000002,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 64784.789999999964,
      "lo": 64784.789999999964,
      "hi": 64784.789999999964,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005683425000000001,
      "lo": 0.005683425000000001,
      "hi": 0.005683425000000001,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005683425000000001,
      "lo": 0.005683425000000001,
      "hi": 0.005683425000000001,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_full",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 9475,
      "lo": 9475,
      "hi": 9475,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 50831.099999999984,
      "lo": 50831.099999999984,
      "hi": 50831.099999999984,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 56671.020000000004,
      "lo": 56671.020000000004,
      "hi": 56671.020000000004,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005160224999999999,
      "lo": 0.005160224999999999,
      "hi": 0.005160224999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005160224999999999,
      "lo": 0.005160224999999999,
      "hi": 0.005160224999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=ai_inpaint",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 6552.5,
      "lo": 6552.5,
      "hi": 6552.5,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 44818.399999999994,
      "lo": 44818.399999999994,
      "hi": 44818.399999999994,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 52093.520000000004,
      "lo": 52093.520000000004,
      "hi": 52093.520000000004,
      "n": 30,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0039270749999999995,
      "lo": 0.0039270749999999995,
      "hi": 0.0039270749999999995,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0039270749999999995,
      "lo": 0.0039270749999999995,
      "hi": 0.0039270749999999995,
      "n": 30,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=duplicate",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.11351339317396876,
      "n": 30,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 6932,
      "lo": 6932,
      "hi": 6932,
      "n": 68,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 77174.39999999998,
      "lo": 77174.39999999998,
      "hi": 77174.39999999998,
      "n": 68,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 108831.92,
      "lo": 108831.92,
      "hi": 108831.92,
      "n": 68,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0038352352941176475,
      "lo": 0.0038352352941176475,
      "hi": 0.0038352352941176475,
      "n": 68,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0038352352941176475,
      "lo": 0.0038352352941176475,
      "hi": 0.0038352352941176475,
      "n": 68,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 3.469446951953614e-18,
      "hi": 0.05273725818905173,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=genuine",
      "target": "diy:gemini-3.8-flash",
      "value": 0.014492753623188406,
      "lo": 0.002562924644588474,
      "hi": 0.07763122461144727,
      "n": 69,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 5245,
      "lo": 5245,
      "hi": 5245,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 8032.5,
      "lo": 8032.5,
      "hi": 8032.5,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 8377.7,
      "lo": 8377.7,
      "hi": 8377.7,
      "n": 11,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0033430909090909093,
      "lo": 0.0033430909090909093,
      "hi": 0.0033430909090909093,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0033430909090909093,
      "lo": 0.0033430909090909093,
      "hi": 0.0033430909090909093,
      "n": 11,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=hard_negative",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2588329669680317,
      "n": 11,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 9217.5,
      "lo": 9217.5,
      "hi": 9217.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 24775.85,
      "lo": 24775.85,
      "hi": 24775.85,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 25231.97,
      "lo": 25231.97,
      "hi": 25231.97,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058292249999999995,
      "lo": 0.0058292249999999995,
      "hi": 0.0058292249999999995,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058292249999999995,
      "lo": 0.0058292249999999995,
      "hi": 0.0058292249999999995,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "class=manual_edit",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 7119,
      "lo": 7119,
      "hi": 7119,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 62782.64999999996,
      "lo": 62782.64999999996,
      "hi": 62782.64999999996,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 107704.64,
      "lo": 107704.64,
      "hi": 107704.64,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004036933333333335,
      "lo": 0.004036933333333335,
      "hi": 0.004036933333333335,
      "n": 90,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004036933333333335,
      "lo": 0.004036933333333335,
      "hi": 0.004036933333333335,
      "n": 90,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=IDR",
      "target": "diy:gemini-3.8-flash",
      "value": 0.01098901098901099,
      "lo": 0.0019424713318492125,
      "hi": 0.05964935668650616,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 6864,
      "lo": 6864,
      "hi": 6864,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 42000.899999999994,
      "lo": 42000.899999999994,
      "hi": 42000.899999999994,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 52521.23999999999,
      "lo": 52521.23999999999,
      "hi": 52521.23999999999,
      "n": 40,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0042262875,
      "lo": 0.0042262875,
      "hi": 0.0042262875,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0042262875,
      "lo": 0.0042262875,
      "hi": 0.0042262875,
      "n": 40,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "currency=USD",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08762160119728664,
      "n": 40,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 7229.5,
      "lo": 7229.5,
      "hi": 7229.5,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 54398.5,
      "lo": 54398.5,
      "hi": 54398.5,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 100108.40000000018,
      "lo": 100108.40000000018,
      "hi": 100108.40000000018,
      "n": 146,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0042826643835616445,
      "lo": 0.0042826643835616445,
      "hi": 0.0042826643835616445,
      "n": 146,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0042826643835616445,
      "lo": 0.0042826643835616445,
      "hi": 0.0042826643835616445,
      "n": 146,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.02546686335923391,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "docType=receipt",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006802721088435374,
      "lo": 0.0012018583516737805,
      "hi": 0.03752395924757055,
      "n": 147,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 9806,
      "lo": 9806,
      "hi": 9806,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 38668.699999999975,
      "lo": 38668.699999999975,
      "hi": 38668.699999999975,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 54238.54000000002,
      "lo": 54238.54000000002,
      "hi": 54238.54000000002,
      "n": 12,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006170375,
      "lo": 0.006170375,
      "hi": 0.006170375,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006170375,
      "lo": 0.006170375,
      "hi": 0.006170375,
      "n": 12,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "editedField=total",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 2.7755575615628914e-17,
      "hi": 0.24249400665524085,
      "n": 12,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 7226,
      "lo": 7226,
      "hi": 7226,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 41614.99999999999,
      "lo": 41614.99999999999,
      "hi": 41614.99999999999,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 51802.04000000003,
      "lo": 51802.04000000003,
      "hi": 51802.04000000003,
      "n": 45,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.00435735,
      "lo": 0.00435735,
      "hi": 0.00435735,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0.00435735,
      "lo": 0.00435735,
      "hi": 0.00435735,
      "n": 45,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=en",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.07865159873288836,
      "n": 45,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 7119,
      "lo": 7119,
      "hi": 7119,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 62782.64999999996,
      "lo": 62782.64999999996,
      "hi": 62782.64999999996,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 107704.64,
      "lo": 107704.64,
      "hi": 107704.64,
      "n": 90,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004036933333333335,
      "lo": 0.004036933333333335,
      "hi": 0.004036933333333335,
      "n": 90,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.004036933333333335,
      "lo": 0.004036933333333335,
      "hi": 0.004036933333333335,
      "n": 90,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.04050400392888021,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "lang=id",
      "target": "diy:gemini-3.8-flash",
      "value": 0.01098901098901099,
      "lo": 0.0019424713318492125,
      "hi": 0.05964935668650616,
      "n": 91,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 9984.5,
      "lo": 9984.5,
      "hi": 9984.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 25548.399999999998,
      "lo": 25548.399999999998,
      "hi": 25548.399999999998,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 26782.48,
      "lo": 26782.48,
      "hi": 26782.48,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0053553,
      "lo": 0.0053553,
      "hi": 0.0053553,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0053553,
      "lo": 0.0053553,
      "hi": 0.0053553,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=explicit_amounts",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 10731.5,
      "lo": 10731.5,
      "hi": 10731.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 58217.449999999975,
      "lo": 58217.449999999975,
      "hi": 58217.449999999975,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 67310.69,
      "lo": 67310.69,
      "hi": 67310.69,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006011549999999999,
      "lo": 0.006011549999999999,
      "hi": 0.006011549999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0.006011549999999999,
      "lo": 0.006011549999999999,
      "hi": 0.006011549999999999,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "prompt=free",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 12706,
      "lo": 12706,
      "hi": 12706,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 58703.65000000001,
      "lo": 58703.65000000001,
      "hi": 58703.65000000001,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 67407.93,
      "lo": 67407.93,
      "hi": 67407.93,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058668,
      "lo": 0.0058668,
      "hi": 0.0058668,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058668,
      "lo": 0.0058668,
      "hi": 0.0058668,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=intact",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 6741,
      "lo": 6741,
      "hi": 6741,
      "n": 109,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 54213.399999999994,
      "lo": 54213.399999999994,
      "hi": 54213.399999999994,
      "n": 109,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 105890.76000000002,
      "lo": 105890.76000000002,
      "hi": 105890.76000000002,
      "n": 109,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003810846330275232,
      "lo": 0.003810846330275232,
      "hi": 0.003810846330275232,
      "n": 109,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003810846330275232,
      "lo": 0.003810846330275232,
      "hi": 0.003810846330275232,
      "n": 109,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.033743935298164184,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.00909090909090909,
      "lo": 0.0016065753043216016,
      "hi": 0.0497056520793305,
      "n": 110,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 9806,
      "lo": 9806,
      "hi": 9806,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 25091.300000000014,
      "lo": 25091.300000000014,
      "hi": 25091.300000000014,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 40478.25999999997,
      "lo": 40478.25999999997,
      "hi": 40478.25999999997,
      "n": 20,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005311350000000001,
      "lo": 0.005311350000000001,
      "hi": 0.005311350000000001,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005311350000000001,
      "lo": 0.005311350000000001,
      "hi": 0.005311350000000001,
      "n": 20,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "provenance=stripped",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.16112515805281938,
      "n": 20,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 6859,
      "lo": 6859,
      "hi": 6859,
      "n": 75,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 72982.79999999996,
      "lo": 72982.79999999996,
      "hi": 72982.79999999996,
      "n": 75,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 108473.24000000002,
      "lo": 108473.24000000002,
      "hi": 108473.24000000002,
      "n": 75,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003732200000000002,
      "lo": 0.003732200000000002,
      "hi": 0.003732200000000002,
      "n": 75,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003732200000000002,
      "lo": 0.003732200000000002,
      "hi": 0.003732200000000002,
      "n": 75,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.048113585065137326,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=cord",
      "target": "diy:gemini-3.8-flash",
      "value": 0.013157894736842105,
      "lo": 0.00232648004557906,
      "hi": 0.07083674751784413,
      "n": 76,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 9217.5,
      "lo": 9217.5,
      "hi": 9217.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 24775.85,
      "lo": 24775.85,
      "hi": 24775.85,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 25231.97,
      "lo": 25231.97,
      "hi": 25231.97,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058292249999999995,
      "lo": 0.0058292249999999995,
      "hi": 0.0058292249999999995,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0058292249999999995,
      "lo": 0.0058292249999999995,
      "hi": 0.0058292249999999995,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=edited:sharp-patch",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 6586,
      "lo": 6586,
      "hi": 6586,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 40278.45,
      "lo": 40278.45,
      "hi": 40278.45,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 42655.36000000001,
      "lo": 42655.36000000001,
      "hi": 42655.36000000001,
      "n": 34,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003984330882352942,
      "lo": 0.003984330882352942,
      "hi": 0.003984330882352942,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0.003984330882352942,
      "lo": 0.003984330882352942,
      "hi": 0.003984330882352942,
      "n": 34,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=expressexpense",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.10151455415332376,
      "n": 34,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 10347.5,
      "lo": 10347.5,
      "hi": 10347.5,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 50462.14999999995,
      "lo": 50462.14999999995,
      "hi": 50462.14999999995,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 65759.63,
      "lo": 65759.63,
      "hi": 65759.63,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005609475000000001,
      "lo": 0.005609475000000001,
      "hi": 0.005609475000000001,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005609475000000001,
      "lo": 0.005609475000000001,
      "hi": 0.005609475000000001,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gemini-nano-banana-2.1",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 10966,
      "lo": 10966,
      "hi": 10966,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 40960.34999999999,
      "lo": 40960.34999999999,
      "hi": 40960.34999999999,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 43652.07,
      "lo": 43652.07,
      "hi": 43652.07,
      "n": 10,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005757375,
      "lo": 0.005757375,
      "hi": 0.005757375,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0.005757375,
      "lo": 0.005757375,
      "hi": 0.005757375,
      "n": 10,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "source=generated:gpt-image-2.5-flare",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.2775327998628892,
      "n": 10,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 6995,
      "lo": 6995,
      "hi": 6995,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 93075.80000000002,
      "lo": 93075.80000000002,
      "hi": 93075.80000000002,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 110317.87999999999,
      "lo": 110317.87999999999,
      "hi": 110317.87999999999,
      "n": 39,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0038243076923076933,
      "lo": 0.0038243076923076933,
      "hi": 0.0038243076923076933,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0038243076923076933,
      "lo": 0.0038243076923076933,
      "hi": 0.0038243076923076933,
      "n": 39,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=exclusive",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.08966685370757144,
      "n": 39,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p50_ms",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 6695,
      "lo": 6695,
      "hi": 6695,
      "n": 32,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p95_ms",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 49195.09999999999,
      "lo": 49195.09999999999,
      "hi": 49195.09999999999,
      "n": 32,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "latency_p99_ms",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 72719.17000000004,
      "lo": 72719.17000000004,
      "hi": 72719.17000000004,
      "n": 32,
      "unit": "ms",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0036073125,
      "lo": 0.0036073125,
      "hi": 0.0036073125,
      "n": 32,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "model_cost_per_check_usd",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.0036073125,
      "lo": 0.0036073125,
      "hi": 0.0036073125,
      "n": 32,
      "unit": "usd",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "error_rate",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "refusal_rate",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0,
      "lo": 0,
      "hi": 0.10426999754245206,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    },
    {
      "task": "operations",
      "metric": "timeout_rate",
      "stratum": "taxMode=none",
      "target": "diy:gemini-3.8-flash",
      "value": 0.030303030303030304,
      "lo": 0.00536941053687183,
      "hi": 0.1531872538211892,
      "n": 33,
      "unit": "rate",
      "higherIsBetter": false
    }
  ],
  "findings": {
    "losses": [
      "authenticity, genuine receipts flagged at risk ≥ 0.5: Receipt Audit (Gemini 3.8 Flash) 25% [16.8%–35.5%] (n=80) vs Claude Haiku 5.5, plain prompt 1.3% [0.2%–6.7%] (n=80).",
      "authenticity, genuine receipts flagged at risk ≥ 0.5: Receipt Audit (Gemini 3.8 Flash) 25% [16.8%–35.5%] (n=80) vs Gemini 3.8 Flash, plain prompt 1.3% [0.2%–6.7%] (n=80).",
      "operations, cost per check to the caller: Receipt Audit (Gemini 3.8 Flash) $0.016 (n=146) vs Claude Haiku 5.5, plain prompt $0.0010 (n=150).",
      "operations, cost per check to the caller: Receipt Audit (Gemini 3.8 Flash) $0.016 (n=146) vs Gemini 3.8 Flash, plain prompt $0.0043 (n=149).",
      "operations, cost per check to the caller: Receipt Audit (Claude Haiku 5.5) $0.016 (n=150) vs Claude Haiku 5.5, plain prompt $0.0010 (n=150).",
      "operations, cost per check to the caller: Receipt Audit (Claude Haiku 5.5) $0.016 (n=150) vs Gemini 3.8 Flash, plain prompt $0.0043 (n=149).",
      "operations, model cost per check: Receipt Audit (Gemini 3.8 Flash) $0.0034 (n=146) vs Claude Haiku 5.5, plain prompt $0.0010 (n=150)."
    ],
    "wins": [
      "extraction, documents with every labelled field right: Receipt Audit (Gemini 3.8 Flash) 95% [89.5%–97.7%] (n=120) vs Claude Haiku 5.5, plain prompt 83.3% [75.7%–88.9%] (n=120).",
      "extraction, documents with every labelled field right: Receipt Audit (Claude Haiku 5.5) 98.3% [94.1%–99.5%] (n=120) vs Claude Haiku 5.5, plain prompt 83.3% [75.7%–88.9%] (n=120).",
      "duplicates, resubmitted copies recognised: Receipt Audit (Gemini 3.8 Flash) 63.3% [45.5%–78.1%] (n=30); Claude Haiku 5.5, plain prompt can't do this task.",
      "duplicates, resubmitted copies recognised: Receipt Audit (Gemini 3.8 Flash) 63.3% [45.5%–78.1%] (n=30); Gemini 3.8 Flash, plain prompt can't do this task.",
      "duplicates, resubmitted copies recognised: Receipt Audit (Claude Haiku 5.5) 63.3% [45.5%–78.1%] (n=30); Claude Haiku 5.5, plain prompt can't do this task.",
      "duplicates, resubmitted copies recognised: Receipt Audit (Claude Haiku 5.5) 63.3% [45.5%–78.1%] (n=30); Gemini 3.8 Flash, plain prompt can't do this task.",
      "operations, model cost per check: Receipt Audit (Gemini 3.8 Flash) $0.0034 (n=146) vs Gemini 3.8 Flash, plain prompt $0.0043 (n=149).",
      "operations, model cost per check: Receipt Audit (Claude Haiku 5.5) $0.00085 (n=150) vs Gemini 3.8 Flash, plain prompt $0.0043 (n=149).",
      "operations, median latency: Receipt Audit (Gemini 3.8 Flash) 4,391 ms (n=146) vs Claude Haiku 5.5, plain prompt 7,254 ms (n=150).",
      "operations, median latency: Receipt Audit (Gemini 3.8 Flash) 4,391 ms (n=146) vs Gemini 3.8 Flash, plain prompt 7,251 ms (n=149).",
      "operations, median latency: Receipt Audit (Claude Haiku 5.5) 5,404 ms (n=150) vs Claude Haiku 5.5, plain prompt 7,254 ms (n=150).",
      "operations, median latency: Receipt Audit (Claude Haiku 5.5) 5,404 ms (n=150) vs Gemini 3.8 Flash, plain prompt 7,251 ms (n=149)."
    ],
    "ties": [
      "extraction, documents with every labelled field right: Receipt Audit (Gemini 3.8 Flash) 95% [89.5%–97.7%] (n=120) vs Gemini 3.8 Flash, plain prompt 90.8% [84.3%–94.8%] (n=120).",
      "extraction, documents with every labelled field right: Receipt Audit (Claude Haiku 5.5) 98.3% [94.1%–99.5%] (n=120) vs Gemini 3.8 Flash, plain prompt 90.8% [84.3%–94.8%] (n=120).",
      "extraction, total read right: Receipt Audit (Gemini 3.8 Flash) 95% [89.5%–97.7%] (n=120) vs Claude Haiku 5.5, plain prompt 95.8% [90.6%–98.2%] (n=120).",
      "extraction, total read right: Receipt Audit (Gemini 3.8 Flash) 95% [89.5%–97.7%] (n=120) vs Gemini 3.8 Flash, plain prompt 98.3% [94.1%–99.5%] (n=120).",
      "extraction, total read right: Receipt Audit (Claude Haiku 5.5) 98.3% [94.1%–99.5%] (n=120) vs Claude Haiku 5.5, plain prompt 95.8% [90.6%–98.2%] (n=120).",
      "extraction, total read right: Receipt Audit (Claude Haiku 5.5) 98.3% [94.1%–99.5%] (n=120) vs Gemini 3.8 Flash, plain prompt 98.3% [94.1%–99.5%] (n=120).",
      "extraction, line-item F1: Receipt Audit (Gemini 3.8 Flash) 93.1% [87.5%–97.5%] (n=98) vs Claude Haiku 5.5, plain prompt 91.2% [84.6%–95.6%] (n=98).",
      "extraction, line-item F1: Receipt Audit (Gemini 3.8 Flash) 93.1% [87.5%–97.5%] (n=98) vs Gemini 3.8 Flash, plain prompt 94.1% [88.8%–98.1%] (n=98).",
      "extraction, line-item F1: Receipt Audit (Claude Haiku 5.5) 93.8% [88.1%–97.9%] (n=98) vs Claude Haiku 5.5, plain prompt 91.2% [84.6%–95.6%] (n=98).",
      "extraction, line-item F1: Receipt Audit (Claude Haiku 5.5) 93.8% [88.1%–97.9%] (n=98) vs Gemini 3.8 Flash, plain prompt 94.1% [88.8%–98.1%] (n=98).",
      "authenticity, ROC AUC, genuine vs fake: Receipt Audit (Gemini 3.8 Flash) 0.815 [0.725–0.896] (n=120) vs Claude Haiku 5.5, plain prompt 0.869 [0.782–0.939] (n=120).",
      "authenticity, ROC AUC, genuine vs fake: Receipt Audit (Gemini 3.8 Flash) 0.815 [0.725–0.896] (n=120) vs Gemini 3.8 Flash, plain prompt 0.907 [0.825–0.972] (n=120).",
      "authenticity, ROC AUC, genuine vs fake: Receipt Audit (Claude Haiku 5.5) 0.888 [0.816–0.954] (n=120) vs Claude Haiku 5.5, plain prompt 0.869 [0.782–0.939] (n=120).",
      "authenticity, ROC AUC, genuine vs fake: Receipt Audit (Claude Haiku 5.5) 0.888 [0.816–0.954] (n=120) vs Gemini 3.8 Flash, plain prompt 0.907 [0.825–0.972] (n=120).",
      "authenticity, fakes caught at a 5% false-flag rate: Receipt Audit (Gemini 3.8 Flash) 55% [40%–75%] (n=40) vs Claude Haiku 5.5, plain prompt 70% [50%–82.5%] (n=40).",
      "authenticity, fakes caught at a 5% false-flag rate: Receipt Audit (Gemini 3.8 Flash) 55% [40%–75%] (n=40) vs Gemini 3.8 Flash, plain prompt 85% [72.5%–95%] (n=40).",
      "authenticity, fakes caught at a 5% false-flag rate: Receipt Audit (Claude Haiku 5.5) 75% [47.5%–90%] (n=40) vs Claude Haiku 5.5, plain prompt 70% [50%–82.5%] (n=40).",
      "authenticity, fakes caught at a 5% false-flag rate: Receipt Audit (Claude Haiku 5.5) 75% [47.5%–90%] (n=40) vs Gemini 3.8 Flash, plain prompt 85% [72.5%–95%] (n=40).",
      "authenticity, fakes whose amounts add up, caught at a 5% false-flag rate (arithmetic=consistent): Receipt Audit (Gemini 3.8 Flash) 46.2% [26.9%–65.4%] (n=26) vs Claude Haiku 5.5, plain prompt 53.8% [30.8%–73.1%] (n=26).",
      "authenticity, fakes whose amounts add up, caught at a 5% false-flag rate (arithmetic=consistent): Receipt Audit (Gemini 3.8 Flash) 46.2% [26.9%–65.4%] (n=26) vs Gemini 3.8 Flash, plain prompt 76.9% [57.7%–92.3%] (n=26).",
      "authenticity, fakes whose amounts add up, caught at a 5% false-flag rate (arithmetic=consistent): Receipt Audit (Claude Haiku 5.5) 65.4% [38.5%–88.5%] (n=26) vs Claude Haiku 5.5, plain prompt 53.8% [30.8%–73.1%] (n=26).",
      "authenticity, fakes whose amounts add up, caught at a 5% false-flag rate (arithmetic=consistent): Receipt Audit (Claude Haiku 5.5) 65.4% [38.5%–88.5%] (n=26) vs Gemini 3.8 Flash, plain prompt 76.9% [57.7%–92.3%] (n=26).",
      "authenticity, genuine receipts flagged at risk ≥ 0.5: Receipt Audit (Claude Haiku 5.5) 1.3% [0.2%–6.7%] (n=80) vs Claude Haiku 5.5, plain prompt 1.3% [0.2%–6.7%] (n=80).",
      "authenticity, genuine receipts flagged at risk ≥ 0.5: Receipt Audit (Claude Haiku 5.5) 1.3% [0.2%–6.7%] (n=80) vs Gemini 3.8 Flash, plain prompt 1.3% [0.2%–6.7%] (n=80).",
      "operations, model cost per check: Receipt Audit (Claude Haiku 5.5) $0.00085 (n=150) vs Claude Haiku 5.5, plain prompt $0.0010 (n=150)."
    ]
  },
  "datasets": [
    {
      "name": "CORD v2 (naver-clova-ix/cord-v2)",
      "license": "CC-BY-4.0",
      "url": "https://huggingface.co/datasets/naver-clova-ix/cord-v2",
      "cases": 76
    },
    {
      "name": "ExpressExpense SRD (sample receipt dataset)",
      "license": "MIT",
      "url": "https://expressexpense.com/blog/free-receipt-images-ocr-machine-learning-dataset/",
      "cases": 34
    },
    {
      "name": "RA-Bench generated fakes",
      "license": "CC-BY-4.0",
      "url": null,
      "cases": 20
    },
    {
      "name": "RA-Bench fakes from CORD v2",
      "license": "CC-BY-4.0",
      "url": null,
      "cases": 14
    },
    {
      "name": "RA-Bench fakes from ExpressExpense SRD",
      "license": "MIT",
      "url": null,
      "cases": 6
    }
  ],
  "limitations": [
    "Preliminary: small samples, so intervals are wide. Read the intervals, not the point estimates.",
    "Public cases come from datasets that are probably in the models' training data.",
    "The DIY baselines use one plain prompt; a stronger prompt would do better. A strong-prompt baseline comes later.",
    "DIY targets have no memory across checks and no deterministic checks: those tasks are marked not supported, not scored as zero.",
    "Our engine runs in process, so its latency has no network hop to receiptaudit.com; DIY latency includes the round trip to the model.",
    "Costs are model tokens at list price on the price date; no infrastructure cost is included.",
    "When the Claude baseline's config says transport claude-code-cli, it ran through Claude Code's CLI on a subscription: thinking is adaptive and can't be fully turned off, its cost is what the same tokens cost through the API, and its latency includes the CLI's start-up.",
    "The duplicate network starts empty for each repetition: it only knows the run's own earlier cases, not production traffic."
  ],
  "examples": [],
  "methodology": "RA-Bench 0.1.0. These definitions, thresholds and exclusions were written before the run and change only in a new suite version.\n\nWho and what. Receipt Audit runs this benchmark on its own product. Every target gets the same cases, the same files, the same timeout (180 s per attempt by default) and the same scoring; only the target changes. A target is our engine (\"self\", in process, with the duplicate network on an empty in-memory backend that lives for one repetition) or an agent's own model asked with one plain prompt (\"diy\"). DIY targets get the same file preparation as our engine (upright, at most 3072 px and 3.75 MB) so that API size limits don't count against them. Transport failures (network errors, HTTP 408, 429 and 5xx) are retried up to 3 times with exponential backoff; nothing else is retried, and a wrong answer is a result. Models are pinned: no fallback to another model.\n\nUnits and intervals. A case run several times counts once, with the share of its runs that succeeded. Rates carry a 95% Wilson interval over cases (operations rates: over calls). ROC AUC, detection at a fixed false-flag rate and line-item F1 carry a 95% percentile bootstrap interval (2000 resamples, genuine receipts and fakes resampled separately, seeded per row so a re-scored run gives the same interval). Latency and cost have no interval. Every row reports n. Rows are given for all cases and for every stratum (a \"dimension=value\" tag on the case, or a label-derived group) with at least 10 cases.\n\nWhich cases count. Extraction, checks and authenticity use base cases only: cases that aren't a transform of another case (no lineage). Duplicate transforms count only for the duplicates task. Operations use every call.\n\nExtraction. Scored only on fields the label covers; a field labelled null means the document doesn't show it, and only a null answer is right. Merchant name: lowercase, accents stripped, \"&\" read as \"and\", punctuation dropped, then a match at edit-distance similarity ≥ 0.9. Date: the exact ISO date (YYYY-MM-DD). Subtotal, tax total and total: within 0.01. Currency: the exact ISO 4217 code. Receipt number: equal after keeping only letters and digits, lowercased. \"All fields right\": every labelled scalar field of the document right in that run (line items excluded). Line-item F1: labelled and extracted items paired one to one when descriptions are at least 0.8 alike (same normalisation) and totals match within 0.01, micro-averaged over all documents. Valid output: the call succeeded and returned readable fields. A failed call or an unreadable answer gets every field wrong.\n\nChecks. totals_add_up is scored against the label \"the printed amounts add up\". A positive is a document whose amounts don't add up; the check flags it when it reports failed. Recall over documents that don't add up; precision over documents it flagged; false alarms over genuine documents that do add up; coverage is the share of documents where the check ran (a check that couldn't run isn't output). Targets without deterministic checks report this task as not supported.\n\nAuthenticity (genuine vs fake). Higher risk means more likely fake. ROC AUC uses each target's risk as the score; a result without a risk scores 0.5 (no opinion), ties count half. Detection at a 1%, 5% and 10% false-flag rate: the share of fakes flagged by the lowest threshold that flags at most that share of genuine receipts (ties at the threshold are all flagged). At the documented thresholds risk ≥ 0.5 and risk ≥ 0.7: the share of fakes flagged (detection) and of genuine receipts flagged (false flags); a result without a risk is never flagged. Strata from the labels: each fake class (\"class=ai_full\", …) and fakes whose amounts add up or don't (\"arithmetic=consistent\", \"arithmetic=inconsistent\"), each compared with every genuine receipt; and provenance metadata (\"provenance=intact\", \"stripped\", \"none\"), genuine receipts and fakes alike.\n\nDuplicates. Every case is submitted by a different account, so a repeat is \"someone else submitted this receipt before\". Recall: the share of duplicate transforms (re-encoded, cropped, re-shot copies of an earlier case) the target recognised as seen before; exact recall counts only matches on the identical image hash. False matches: the share of distinct receipts reported as seen before, for hard negatives (different receipts that look alike: same merchant, template or day; \"false_match_rate\") and for the other genuine receipts (\"false_match_rate_genuine\"). Originals always run before their transforms. Targets without memory across checks (DIY prompts) report the task as not supported, not as zero.\n\nOperations. Latency: wall time of the final attempt of each successful call, measured by the harness (p50, p95, p99). Cost per check is what the caller pays for one check: for Receipt Audit, the list price of its smallest credit pack per check; for a DIY baseline, its model tokens × the AI Gateway list price on the run's price date. Model cost per check is the model tokens × that list price for every target, our engine's own model call included (infrastructure not included). Both are averaged over successful calls. Error, refusal and timeout rates over all calls.\n\nFindings. Each of our targets is compared with each baseline on the headline rows of every task (stratum \"all\"): a win or a loss only when the 95% intervals don't overlap, otherwise a tie; for latency and cost, which have no interval, only when one value is at least 1.2 times the other. A comparison resting on fewer than 10 cases (or calls) on either side is always a tie. A task a baseline can't do by construction is reported as such, not as a score of zero.",
  "reproduce": {
    "repo": null,
    "command": "cd apps/receipt-check && nub run bench run --cases benchmarks/receipt-audit/cases.jsonl --split public --targets self,self-haiku,diy:claude-haiku-5.5,diy:gemini-3.8-flash --reps 1"
  },
  "history": []
}