nucleic-purpose-classifier/data/curation-review-v1.json

{
  "schemaVersion": 1,
  "datasetVersion": "purpose-dataset-v1",
  "wordTrigramExclusionReview": {
    "status": "complete",
    "reviewedRecords": 18,
    "confirmedTemplateDuplicates": 18,
    "rejectedExclusions": 0,
    "decision": "All 18 pairs preserve the same task, requested outcome, and purpose label; differences are generated identifiers, ticket numbers, cosmetic context prefixes, or difficulty/slice metadata. Keep the earliest member and exclude the later template copy.",
    "reviewedDroppedPromptHashes": [
      "f29de1d646055017f80346055bb3ac1468c49af7ab0c6249f45f19cf386f9fa7",
      "dabbcd0a19d2918199b5d0d35fac49fd5413cb17a5164252b789114fc68ec43b",
      "ac3a166e07a1db67475c773ef3d996d12fe627d11b7bb91a7c524c9c67c841b0",
      "d5f9d735490874ded856105e10df99ed3c2c703c09ec7909fd07aa1e9e7a0c91",
      "6376e5f6f0d7c3d6faae9e50975034113f43a7f959bcbbea67531d3b4f0cfd16",
      "10933534254a1f73163e0ba7883225e2d0c896b565590753698c1052743af664",
      "cf4deb437c380216601b176e238964bfce79bf2645d54e1eb659f8479b980186",
      "fe6b2e05da51a12ea07d6fa015933196931fb1023b62c0eb267b80318f083ba0",
      "c0fddb025279caf6438453b53c99b266ccfb61c6c19609b43c6f731d88812813",
      "15c28d9f67ba103378db711c82193aba7330acbe602d9df54995a5db20e1bbb1",
      "b3583a130811ba7d2f425042c41e1f69244c622764a0c952ed42bb5114e18735",
      "bba760782054c4ed405611cf8b55bc99d710424bb3f9bab0682dc2c1cf4e2a52",
      "bd4d2d8ea68a4e56eaed5c6465815abefa6c8ae78fb533eb81547dedac9c71ed",
      "8c1ab1a866cadd294c3d2a6c1d6eefbede62549220c81e1dd28a886717aa285d",
      "c074ce20e7cd81c28d390aed919bab30cabe9211817103e52c9b229e6a3c94ff",
      "fdc04376376dbffcaf9928e9edcef29376203640b49c200c2c117f78891125a1",
      "432e67ead52d6cd57e4a5034cd8bcde14bd2da13f88cb5532c42fd8fbd8daf05",
      "24f3759ff4a3fb9fc77bed4c8525f30f9af2479a6cffbb0c4842043f99a7d8f1"
    ]
  },
  "semanticDuplicateReview": {
    "status": "complete",
    "auditVersion": "purpose-semantic-audit-v1",
    "reviewedCandidates": 4,
    "excludedCandidates": 3,
    "retainedCandidates": 1,
    "decision": "Exclude three same-purpose generated template copies. One pair ('make the screen nicer' / 'Make this screen nicer') remains because it is a deliberate vague-language variant, lives entirely in validation, and does not contaminate the frozen evaluation boundary.",
    "excluded": [
      {
        "droppedPromptHash": "7348d764d602cfff72dd2b1d369ad0375a96ea52b38174aa0bd6168a548bcc2f",
        "matchedPromptHash": "3ad9cfbb664504f0e7ae84b905520937e7812d4e879fa706415782341f2cd400",
        "similarity": 0.984897
      },
      {
        "droppedPromptHash": "a0c6e7984e92adc11ea6855c39688d733bf7665f5f965939325b15f3ba39e937",
        "matchedPromptHash": "17f79a890a323c08770193a94b100dadaa00116405bdb7d14c1b89abc3c3066a",
        "similarity": 0.980998
      },
      {
        "droppedPromptHash": "bfd7791069fd04c13797f39ba99224ad68ca2deebbc912f08b10815954a7d223",
        "matchedPromptHash": "dc48031efb18f25a56a3beddcdd814f26473b23cd496482ce1884ae6f697417a",
        "similarity": 0.973329
      }
    ],
    "retained": [
      {
        "leftPromptHash": "70944e70e0062e947476f73b704ec01ecee19420d06fd174c58a41c04e8112f6",
        "rightPromptHash": "cb3e63992cbf5830a222933dc7b44be39933baedcb46e335be02e3c379685517",
        "similarity": 0.970376
      }
    ]
  },
  "humanLabelAndDifficultyReview": {
    "status": "planned",
    "populationRecords": 12193,
    "sampleFraction": 0.1,
    "sampleRecords": 1219,
    "seed": 10558743,
    "strata": [
      "purpose",
      "slice",
      "primary language"
    ],
    "reviewFields": [
      "purpose",
      "secondary",
      "difficulty",
      "slice",
      "review status",
      "notes"
    ],
    "generatedArtifact": "ml/purpose-classifier/.artifacts/human-review-v1.csv",
    "completionRule": "Every sampled row must be marked accept, relabel, or reject by a human reviewer. review_data.py validates the exact sample and writes a versioned complete ledger; prepare_data.py applies relabel/reject decisions before splitting. The revised split and frozen evaluation must then be intentionally reviewed and versioned before the dataset can be called fully curated."
  }
}