{
 "id": "tattabio/OG",
 "owner": "tattabio",
 "name": "OG",
 "downloads": 536,
 "likes": 2,
 "last_modified": "2024-08-19T20:57:44.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{Cornman2024,\n  title = {The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modeling},\n  url = {https://www.biorxiv.org/content/early/2024/08/17/2024.08.14.607850},\n  DOI = {10.1101/2024.08.14.607850},\n  publisher = {Cold Spring Harbor Laboratory},\n  author = {Cornman, Andre and West-Roberts, Jacob and Camargo, Antonio Pedro and Roux, Simon and Beracochea, Martin and Mirdita, Milot and Ovchinnikov, Sergey and Hwang, Yunha},\n  year = {2024},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "fefca520e2837d24a0fa0114268ec07a4d0b7da6",
 "stated_evidence": "https://huggingface.co/datasets/tattabio/OG/blob/fefca520e2837d24a0fa0114268ec07a4d0b7da6/README.md",
 "file_evidence": "https://huggingface.co/datasets/tattabio/OG/tree/fefca520e2837d24a0fa0114268ec07a4d0b7da6",
 "card_nc": false
}