{
  "curation": {
    "excludedDuplicates": {
      "near": 18
    },
    "inputRecords": 12007,
    "nearDuplicateMethod": "word-trigram Jaccard after SimHash LSH candidate search",
    "nearDuplicateThreshold": 0.92,
    "retainedRecords": 11989,
    "vagueEvalPolicy": "validation/test only"
  },
  "datasetVersion": "purpose-dataset-sol-high-v2",
  "frozenEval": {
    "classifiableShippedFixtureRecords": 89,
    "excludedGeneralFixtureRecords": 3,
    "hardSliceDefinition": [
      "boundary",
      "mixed",
      "pasted-context",
      "vague-eval"
    ],
    "shippedFixtureRecords": 92,
    "shippedFixturesPath": "Tests/NucleicCoreTests/Fixtures/purpose-prompts.json",
    "shippedFixturesSha256": "876068ea26d7109365bcfbd1dc44ba3f1a0400c80dc7fdacf008b3fa07cd92cc",
    "syntheticPath": "ml/purpose-classifier/data/frozen-test-v1.jsonl",
    "syntheticSha256": "9997dbaa6d305ea56d8c161e39b925368761ab613a706eb8c2ba55d0e58b1906"
  },
  "ratios": {
    "test": 0.1,
    "train": 0.8,
    "validation": 0.1
  },
  "schemaVersion": 1,
  "seed": 3248837105,
  "sources": [
    {
      "path": "ml/purpose-classifier/data/purpose-prompts.jsonl",
      "records": 9007,
      "sha256": "6fbd08df113ca4c6f9da151222772dc3e25e1b9b19c9c2b7df9f572053af2507"
    },
    {
      "path": "ml/purpose-classifier/data/purpose-prompts-round2.jsonl",
      "records": 3000,
      "sha256": "a3c5bbede5b7db743c9f31756491990b388edd2aa9b41c8b2b9ec95b7115f4aa"
    }
  ],
  "splits": {
    "test": {
      "classifiableFixtureRecords": 89,
      "distribution": {
        "language": {
          "de": 6,
          "en": 1084,
          "es": 7,
          "fr": 7,
          "ja": 5,
          "pt": 7,
          "zh": 3
        },
        "purpose": {
          "backendImpl": 140,
          "debugging": 168,
          "frontendImpl": 159,
          "planning": 120,
          "quickFix": 136,
          "refactor": 149,
          "review": 131,
          "writing": 116
        },
        "slice": {
          "boundary": 51,
          "core": 635,
          "mixed": 87,
          "pasted-context": 77,
          "vague-eval": 269
        }
      },
      "hardSyntheticRecords": 484,
      "logicalRecords": 1208,
      "sha256": "9997dbaa6d305ea56d8c161e39b925368761ab613a706eb8c2ba55d0e58b1906",
      "syntheticRecords": 1119
    },
    "train": {
      "distribution": {
        "language": {
          "de": 84,
          "en": 9257,
          "es": 82,
          "fr": 64,
          "ja": 62,
          "pt": 56,
          "zh": 57
        },
        "purpose": {
          "backendImpl": 1223,
          "debugging": 1355,
          "frontendImpl": 1092,
          "planning": 1208,
          "quickFix": 1184,
          "refactor": 1204,
          "review": 1203,
          "writing": 1193
        },
        "slice": {
          "boundary": 605,
          "core": 7175,
          "mixed": 987,
          "pasted-context": 895
        }
      },
      "records": 9662,
      "sha256": "0e16940308dc7557c73b1b804bf7b715c86d263b613201588ec274169ee01e89"
    },
    "validation": {
      "distribution": {
        "language": {
          "de": 10,
          "en": 1165,
          "es": 10,
          "fr": 7,
          "ja": 5,
          "pt": 4,
          "zh": 7
        },
        "purpose": {
          "backendImpl": 152,
          "debugging": 182,
          "frontendImpl": 174,
          "planning": 128,
          "quickFix": 140,
          "refactor": 163,
          "review": 143,
          "writing": 126
        },
        "slice": {
          "boundary": 57,
          "core": 677,
          "mixed": 95,
          "pasted-context": 88,
          "vague-eval": 291
        }
      },
      "records": 1208,
      "sha256": "301cd3d1c69e1bb92b811e857093ad12fb8c5c11bb402ee2993403d5e4467969"
    }
  }
}