nucleic-purpose-classifier/data/dataset-v1-manifest.json

{
  "curation": {
    "excludedDuplicates": {
      "near": 18,
      "semantic-reviewed": 3
    },
    "inputRecords": 12214,
    "nearDuplicateMethod": "word-trigram Jaccard after SimHash LSH candidate search",
    "nearDuplicateThreshold": 0.92,
    "retainedRecords": 12193,
    "reviewPath": "ml/purpose-classifier/data/curation-review-v1.json",
    "reviewSha256": "2db763df027b545b4fd654108dcadb0717f9c9c0a63555bf8cea26b791cda370",
    "vagueEvalPolicy": "validation/test only"
  },
  "datasetVersion": "purpose-dataset-v1",
  "frozenEval": {
    "classifiableShippedFixtureRecords": 87,
    "excludedGeneralFixtureRecords": 5,
    "hardSliceDefinition": [
      "boundary",
      "mixed",
      "pasted-context",
      "vague-eval"
    ],
    "shippedFixtureRecords": 92,
    "shippedFixturesPath": "Tests/NucleicCoreTests/Fixtures/purpose-prompts.json",
    "shippedFixturesSha256": "6c8f0eedce35f9da7a407934009e87737b5e85c7371f6a118982d9fae2ea7aae",
    "syntheticPath": "ml/purpose-classifier/data/frozen-test-v1.jsonl",
    "syntheticSha256": "5d34c8ac3d39c5b4e2e739c4c9058093beb6f790a42a1397cedefae6271654ab"
  },
  "ratios": {
    "test": 0.1,
    "train": 0.8,
    "validation": 0.1
  },
  "schemaVersion": 1,
  "seed": 3248837105,
  "sources": [
    {
      "path": "ml/purpose-classifier/data/purpose-prompts.jsonl",
      "records": 9214,
      "sha256": "3c7f8b496ef2014794a50433a78e3125c0dd4a03dc2a7773b52ee25587ac48e7"
    },
    {
      "path": "ml/purpose-classifier/data/purpose-prompts-round2.jsonl",
      "records": 3000,
      "sha256": "0a35eac2549e95b31518cd0eee99b83b03761c26a0fb258f427fe04a632699ed"
    }
  ],
  "splits": {
    "test": {
      "classifiableFixtureRecords": 87,
      "distribution": {
        "language": {
          "de": 7,
          "en": 1110,
          "es": 9,
          "fr": 5,
          "ja": 3,
          "pt": 4,
          "zh": 3
        },
        "purpose": {
          "backendImpl": 171,
          "debugging": 149,
          "frontendImpl": 157,
          "planning": 132,
          "quickFix": 140,
          "refactor": 136,
          "review": 127,
          "writing": 129
        },
        "slice": {
          "boundary": 179,
          "core": 507,
          "mixed": 80,
          "pasted-context": 84,
          "vague-eval": 291
        }
      },
      "hardSyntheticRecords": 634,
      "logicalRecords": 1228,
      "sha256": "5d34c8ac3d39c5b4e2e739c4c9058093beb6f790a42a1397cedefae6271654ab",
      "syntheticRecords": 1141
    },
    "train": {
      "distribution": {
        "language": {
          "de": 100,
          "en": 9324,
          "es": 100,
          "fr": 81,
          "ja": 77,
          "pt": 70,
          "zh": 72
        },
        "purpose": {
          "backendImpl": 1226,
          "debugging": 1245,
          "frontendImpl": 1234,
          "planning": 1223,
          "quickFix": 1230,
          "refactor": 1223,
          "review": 1230,
          "writing": 1213
        },
        "slice": {
          "boundary": 2066,
          "core": 5818,
          "mixed": 906,
          "pasted-context": 1034
        }
      },
      "records": 9824,
      "sha256": "40a5064c2a95d4394d71b3edbad7d03dce7d67b2e5ba9ab9320476e35e3a4953"
    },
    "validation": {
      "distribution": {
        "language": {
          "de": 8,
          "en": 1178,
          "es": 12,
          "fr": 7,
          "ja": 8,
          "pt": 8,
          "zh": 7
        },
        "purpose": {
          "backendImpl": 183,
          "debugging": 157,
          "frontendImpl": 168,
          "planning": 141,
          "quickFix": 151,
          "refactor": 149,
          "review": 140,
          "writing": 139
        },
        "slice": {
          "boundary": 195,
          "core": 541,
          "mixed": 83,
          "pasted-context": 95,
          "vague-eval": 314
        }
      },
      "records": 1228,
      "sha256": "3d0a3730931db360dd8346cf12d03901ac139acf5be1d9e84975ac591186c588"
    }
  }
}