{
 "id": "HuggingFaceBio/carbon-pretraining-corpus",
 "owner": "HuggingFaceBio",
 "name": "carbon-pretraining-corpus",
 "downloads": 2116,
 "likes": 33,
 "last_modified": "2026-06-18T10:18:15.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{allal2026carbon,\n  title={Carbon: Decoding the Language of Life},\n  author={Allal, Loubna Ben and Li, Qiuyi and Fiusco, Maurizio and Tunstall, Lewis and Rasul, Kashif and Beeching, Ed and Aubakirova, Dana and Pati{\\~n}o, Carlos and Frere, Thibaud and Lozhkov, Anton and others},\n  journal={bioRxiv},\n  pages={2026--05},\n  year={2026},\n  publisher={Cold Spring Harbor Laboratory}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "8541ba4ace7e02ce6a034b0deadf8256d18e4425",
 "stated_evidence": "https://huggingface.co/datasets/HuggingFaceBio/carbon-pretraining-corpus/blob/8541ba4ace7e02ce6a034b0deadf8256d18e4425/README.md",
 "file_evidence": "https://huggingface.co/datasets/HuggingFaceBio/carbon-pretraining-corpus/tree/8541ba4ace7e02ce6a034b0deadf8256d18e4425",
 "card_nc": false
}