datasets/metadata/dataset_metadata.json

{
  "dataset_name": "Kimi-K2.7-CodingTraces-9000x",
  "repository": "trjxter/Kimi-K2.7-CodingTraces-9000x",
  "rows": 9014,
  "teacher_model": "moonshotai/Kimi-K2.7-Code",
  "temperature": 0.6,
  "top_p": 0.95,
  "max_tokens_sent": false,
  "dataset_sha256": "b472dff4318a35dd0eeff9eb8ba39d62520bc4e0946141c35ff5c3321c523fac",
  "schema": [
    "ID",
    "conversation",
    "input",
    "output",
    "domain",
    "meta"
  ],
  "output_contract": "<think>\\nreasoning\\n</think>\\n\\nfinal answer",
  "bucket_counts": {
    "real_world_coding": 2334,
    "code_grounded": 1398,
    "algorithmic_reasoning": 1549,
    "jackrong_general_coding": 1864,
    "specialized_development": 934,
    "repository_engineering": 935
  },
  "source_counts": {
    "m-a-p/CodeFeedback-Filtered-Instruction": 2615,
    "Jackrong/GLM-5.1-Reasoning-1M-Cleaned": 2183,
    "ise-uiuc/Magicoder-OSS-Instruct-75K": 1732,
    "nvidia/OpenCodeReasoning-2": 875,
    "deepmind/code_contests": 674,
    "SWE-bench/SWE-smith-py": 229,
    "SWE-bench/SWE-smith-ts": 149,
    "SWE-bench/SWE-smith-js": 129,
    "SWE-bench/SWE-smith-java": 119,
    "SWE-bench/SWE-smith-cpp": 117,
    "SWE-bench/SWE-smith-rs": 98,
    "SWE-bench/SWE-smith-go": 94
  },
  "language_counts": {
    "python": 3932,
    "unspecified": 1549,
    "javascript": 571,
    "cpp": 483,
    "java": 425,
    "sql": 410,
    "typescript": 315,
    "rust": 280,
    "unknown": 201,
    "php": 150,
    "csharp": 138,
    "swift": 110,
    "html": 107,
    "go": 103,
    "shell": 101,
    "c": 35,
    "css": 33,
    "jsx": 17,
    "json": 14,
    "r": 8,
    "ruby": 6,
    "html_css": 5,
    "assembly": 4,
    "http": 3,
    "scala": 2,
    "xml": 2,
    "regex": 2,
    "dockerfile": 1,
    "racket": 1,
    "sas": 1,
    "yaml": 1,
    "mongodb": 1,
    "graphql": 1,
    "vba": 1,
    "perl": 1
  },
  "token_totals": {
    "prompt_tokens": 4906850,
    "completion_tokens": 43942830,
    "total_tokens": 48849680
  },
  "cleaning": {
    "rows_removed": 0,
    "rows_preserved": 9014,
    "tag_collision_rows_repaired": 2193,
    "repair_policy": "Complete outer reserved-tag wrappers were removed; remaining literal reserved tags inside generated content were HTML-escaped."
  },
  "created_at_utc": "2026-06-22T05:49:01.990877+00:00"
}