{
 "id": "jablonkagroup/chempile-code",
 "owner": "jablonkagroup",
 "name": "chempile-code",
 "downloads": 346,
 "likes": 5,
 "last_modified": "2025-08-13T13:03:48.000Z",
 "stated_licence": "agpl-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "bigcode/the-stack",
   "licence": "other",
   "found": true,
   "evidence": "https://huggingface.co/datasets/bigcode/the-stack/blob/153f6301d232928d7f90d09b37fceb4fadc2c950/README.md"
  },
  {
   "id": "codeparrot/github-code",
   "licence": "other",
   "found": true,
   "evidence": "https://huggingface.co/datasets/codeparrot/github-code/blob/b5661e6b17396364b2bcf8e68977b0d28e1ebd19/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{mirza2025chempile0,\n  title   = {ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models},\n  author  = {Adrian Mirza and Nawaf Alampara and Martiño Ríos-García and others},\n  year    = {2025},\n  journal = {arXiv preprint arXiv:2505.12534}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID for at least one declared source dataset.",
 "revision": "50f1009c6f299f248250d89d80c2c15566c0853a",
 "stated_evidence": "https://huggingface.co/datasets/jablonkagroup/chempile-code/blob/50f1009c6f299f248250d89d80c2c15566c0853a/README.md",
 "file_evidence": "https://huggingface.co/datasets/jablonkagroup/chempile-code/tree/50f1009c6f299f248250d89d80c2c15566c0853a",
 "card_nc": false
}