{
 "id": "almanach/OntoBook",
 "owner": "almanach",
 "name": "OntoBook",
 "downloads": 92,
 "likes": 1,
 "last_modified": "2026-08-02T22:01:16.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@inproceedings{touchent:hal-05697506,\n  TITLE = {{OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining}},\n  AUTHOR = {Touchent, Rian and de la Clergerie, {\\'E}ric},\n  URL = {https://hal.science/hal-05697506},\n  BOOKTITLE = {{Proceedings of Knowledge Graphs and Large Language Models Workshop}},\n  ADDRESS = {Palma de Mallorca, Spain},\n  YEAR = {2026},\n  MONTH = May,\n  PDF = {https://hal.science/hal-05697506v1/file/main.pdf},\n  HAL_ID = {hal-05697506},\n  HAL_VERSION = {v1},\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "87128abc52b744b42a12122962d58bf8f5135a91",
 "stated_evidence": "https://huggingface.co/datasets/almanach/OntoBook/blob/87128abc52b744b42a12122962d58bf8f5135a91/README.md",
 "file_evidence": "https://huggingface.co/datasets/almanach/OntoBook/tree/87128abc52b744b42a12122962d58bf8f5135a91",
 "card_nc": false
}