{
  "auditVersion": "purpose-semantic-audit-v1",
  "candidatePolicy": {
    "automaticExclusion": false,
    "crossLabelCosineThreshold": 0.985,
    "nearestNeighborsPerRecord": 8,
    "note": "Embedding similarity proposes review candidates only. It cannot safely distinguish deliberate boundary pairs from duplicated labels.",
    "sameLabelCosineThreshold": 0.97
  },
  "candidates": [
    {
      "crossesFrozenBoundary": false,
      "left": {
        "line": 4639,
        "origin": "synthetic",
        "promptHash": "70944e70e0062e947476f73b704ec01ecee19420d06fd174c58a41c04e8112f6",
        "purpose": "frontendImpl",
        "source": "ml/purpose-classifier/data/purpose-prompts.jsonl",
        "split": "validation"
      },
      "right": {
        "line": 8435,
        "origin": "synthetic",
        "promptHash": "cb3e63992cbf5830a222933dc7b44be39933baedcb46e335be02e3c379685517",
        "purpose": "frontendImpl",
        "source": "ml/purpose-classifier/data/purpose-prompts.jsonl",
        "split": "validation"
      },
      "sameLabel": true,
      "similarity": 0.970376
    }
  ],
  "embedding": {
    "device": "cpu",
    "fixedInputShape": [
      1,
      128
    ],
    "model": "sentence-transformers/all-MiniLM-L6-v2",
    "pooling": "attention-mask mean pooling followed by L2 normalization",
    "revision": "1110a243fdf4706b3f48f1d95db1a4f5529b4d41",
    "truncation": {
      "headTokens": 63,
      "strategy": "head-tail-pair",
      "tailTokens": 62
    }
  },
  "humanReviewSample": {
    "fraction": 0.1,
    "generatedCSV": "ml/purpose-classifier/.artifacts/human-review-v1.csv",
    "populationRecords": 12193,
    "requiredFields": [
      "reviewedPurpose",
      "reviewedSecondary",
      "reviewedDifficulty",
      "reviewedSlice",
      "reviewStatus"
    ],
    "samplePurposeCounts": {
      "backendImpl": 158,
      "debugging": 154,
      "frontendImpl": 155,
      "planning": 152,
      "quickFix": 150,
      "refactor": 149,
      "review": 150,
      "writing": 151
    },
    "sampleRecords": 1219,
    "sampleSliceCounts": {
      "boundary": 245,
      "core": 689,
      "mixed": 108,
      "pasted-context": 117,
      "vague-eval": 60
    },
    "seed": 10558743,
    "status": "planned",
    "strata": [
      "purpose",
      "slice",
      "primary language"
    ]
  },
  "population": {
    "auditedRecords": 12280,
    "canonicalSourceRecords": 12214,
    "classifiableShippedFixtures": 87,
    "curatedSyntheticRecords": 12193
  },
  "schemaVersion": 1,
  "summary": {
    "candidates": 1,
    "crossLabelCandidates": 0,
    "frozenBoundaryCandidates": 0,
    "sameLabelCandidates": 1
  }
}