{
 "id": "trillionlabs/TheBioCollection-Eval",
 "owner": "trillionlabs",
 "name": "TheBioCollection-Eval",
 "downloads": 341,
 "likes": 2,
 "last_modified": "2026-06-26T06:33:07.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "question-answering"
 ],
 "citation": "@article{TheBioCollection,\ntitle={TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology},\nauthor={Hyunjin Seo and Hyeon Hwang and Gyubok Lee and Jay Shin and Hongjoon Ahn and Sungjun Han and Sangwon Jung},\njournal={arXiv preprint arXiv:XXX},\nyear={2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "4f5b341785f60b9d8965b921ed1918abb5f8bb3d",
 "stated_evidence": "https://huggingface.co/datasets/trillionlabs/TheBioCollection-Eval/blob/4f5b341785f60b9d8965b921ed1918abb5f8bb3d/README.md",
 "file_evidence": "https://huggingface.co/datasets/trillionlabs/TheBioCollection-Eval/tree/4f5b341785f60b9d8965b921ed1918abb5f8bb3d",
 "card_nc": false
}