{
 "id": "storagestuffnobody/stack-v3.1-subsampled",
 "owner": "storagestuffnobody",
 "name": "stack-v3.1-subsampled",
 "downloads": 258,
 "likes": 0,
 "last_modified": "2026-10-21T16:53:09.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "Stars and test/CI paths are heuristics, not measured code quality, successful builds or passing tests.\nNo extra content classifier, family/owner deduplication, language quota, license gate, dependency validation,\ntraining-window construction or evaluation holdout is added. Removing files may leave incomplete dependencies.\nThis subset has not been evaluated for downstream model quality or benchmark contamination.\n\nThis dataset derives from The Stack v3 by Hugging Face / BigCode. See the\n[source dataset card](https://huggingface.co/datasets/HuggingFaceCode/stack-v3-train/blob/1f61b735bc0a5698345ce2196730f24bfa467f33/README.md)\nfor collection, upstream filtering, licensing and removal information, and\n[Am I in The Stack?](https://huggingface.co/spaces/HuggingFaceCode/in-the-stack) for upstream removal requests.\nDatabase attribution follows [ODC-By 1.0](https://opendatacommons.org/licenses/by/1-0/);\nindividual files retain their original license metadata. The included GitHub Linguist taxonomy retains its\n[MIT license](reproduction/linguist-LICENSE).",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "ea897b29c28e2b6dd993987e36af228a3e34986c",
 "stated_evidence": "https://huggingface.co/datasets/storagestuffnobody/stack-v3.1-subsampled/blob/ea897b29c28e2b6dd993987e36af228a3e34986c/README.md",
 "file_evidence": "https://huggingface.co/datasets/storagestuffnobody/stack-v3.1-subsampled/tree/ea897b29c28e2b6dd993987e36af228a3e34986c",
 "card_nc": false
}