manifest.json

{
  "bucket": "Minnimaro/reference-sft-bucket",
  "latest_version": "v1.0.0",
  "versions": [
    {
      "version": "v1.0.0",
      "created_at": "2026-08-15T21:56:09Z",
      "total_rows": 227788,
      "files": [
        {
          "path": "v1.0.0/dataset_card.md",
          "rows": null,
          "bytes": 6901,
          "sha256": "a5f6f0f3d75917dd95a2ef084be2068305228bdd2dca282afcb273264b2c8fce"
        },
        {
          "path": "v1.0.0/schema.json",
          "rows": null,
          "bytes": 4939,
          "sha256": "4dd236725a66479a45bf78bab8d6db2bdf88cbe5b5ea32fe28a53cb2a6c964f0"
        },
        {
          "path": "v1.0.0/spot_checks.json",
          "rows": null,
          "bytes": 116266,
          "sha256": "415156121856e9d205e96f85026535b68e9a143b6ba303dc434f3d1b2a6359bc"
        },
        {
          "path": "v1.0.0/veracity_report.json",
          "rows": null,
          "bytes": 3270,
          "sha256": "e940c37a982572f475dad8f2f33990ce31aee8db48ee7535160f02310a293a31"
        },
        {
          "path": "v1.0.0/data/commonsense_reasoning.parquet",
          "rows": 10000,
          "bytes": 2182284,
          "sha256": "1bee504143c57db34b07898b20217a382c9c9742f93cfe8805b0a3c5af498187"
        },
        {
          "path": "v1.0.0/data/computer_science.parquet",
          "rows": 23199,
          "bytes": 26787907,
          "sha256": "ecef0ca3b1ce40d917c1c494867da779a4621aeffa2e9637564934ae141edf23"
        },
        {
          "path": "v1.0.0/data/conversation.parquet",
          "rows": 13995,
          "bytes": 8948245,
          "sha256": "b175882803109910f2a0e00b81685f5f79b7cbe19605efc5f28e4db4089a566f"
        },
        {
          "path": "v1.0.0/data/education.parquet",
          "rows": 8000,
          "bytes": 4806655,
          "sha256": "4ee8fb2f1adc27503688ac04d9d758fd88090a16e2a670596d5945f8dd66298b"
        },
        {
          "path": "v1.0.0/data/finance.parquet",
          "rows": 1138,
          "bytes": 2129389,
          "sha256": "3e9569a7d4064b23d8bd9e0674a5cf51450608bf4f5a7481670fca23f70c2e41"
        },
        {
          "path": "v1.0.0/data/general_knowledge.parquet",
          "rows": 53119,
          "bytes": 74548897,
          "sha256": "240119349d0d1188e32509bd3d57ec1230b7ae6f493bb6289bafb27e6df0085d"
        },
        {
          "path": "v1.0.0/data/government.parquet",
          "rows": 7989,
          "bytes": 192426527,
          "sha256": "46cd7cfd78ef6742fbfc82d946e5ed07803a64723107d9ac5a28c8be9c9caf68"
        },
        {
          "path": "v1.0.0/data/law.parquet",
          "rows": 10000,
          "bytes": 10117914,
          "sha256": "bd3d694f98fc20bc5d175d83ea0bf965a82670544ed97255f83b6de24375c9b0"
        },
        {
          "path": "v1.0.0/data/literature.parquet",
          "rows": 15972,
          "bytes": 3589201320,
          "sha256": "0bcf6cf60c7fa486a04626b146e8c535b21eba708e55629f0286c59541088a00"
        },
        {
          "path": "v1.0.0/data/mathematics.parquet",
          "rows": 17994,
          "bytes": 6335723,
          "sha256": "12dcfff800bd15d548b721a6eb6c866d3cb318a6fd08f9c36c513f960a1fc04b"
        },
        {
          "path": "v1.0.0/data/medicine.parquet",
          "rows": 17999,
          "bytes": 5602621,
          "sha256": "60300f40769c732e479c0084f4dfa2a476f1d93ddc8b01a529ec6b1848487dda"
        },
        {
          "path": "v1.0.0/data/news.parquet",
          "rows": 15508,
          "bytes": 51639426,
          "sha256": "4ca30ec6c852e29616d12a51a77d439e9b5bf13d555602c32bce1f1fb6aa56ad"
        },
        {
          "path": "v1.0.0/data/reference-sft.parquet",
          "rows": 227788,
          "bytes": 4250676084,
          "sha256": "2d78e1a1c40ae6bf45c6c917f8d841f0d4648218bdeb028f29bc28b91f504b43"
        },
        {
          "path": "v1.0.0/data/science.parquet",
          "rows": 32875,
          "bytes": 276409336,
          "sha256": "45cd3383cc83c44e76d79ad6464afefdd3a5bd3b0289e2ec651f8ee4a2cd0ec3"
        }
      ],
      "domains": {
        "commonsense_reasoning": 10000,
        "computer_science": 23199,
        "conversation": 13995,
        "education": 8000,
        "finance": 1138,
        "general_knowledge": 53119,
        "government": 7989,
        "law": 10000,
        "literature": 15972,
        "mathematics": 17994,
        "medicine": 17999,
        "news": 15508,
        "science": 32875
      },
      "format_split": {
        "instruction_response": 151065,
        "raw_text": 76723
      },
      "veracity_distribution": {
        "3": 13968,
        "4": 73966,
        "5": 139854
      }
    }
  ]
}