{
 "id": "LiteFold/OpenProteinSet",
 "owner": "LiteFold",
 "name": "OpenProteinSet",
 "downloads": 582,
 "likes": 1,
 "last_modified": "2026-05-27T11:41:41.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "feature-extraction",
  "other"
 ],
 "citation": "@inproceedings{ahdritz2023openproteinset,\n  title     = {OpenProteinSet: Training Data for Structural Biology at Scale},\n  author    = {Ahdritz, Gustaf and Bouatta, Nazim and Kadyan, Sachin and Jarosch, Lukas and Berenberg, Daniel and Fisk, Ian and Watkins, Andrew M. and Ra, Stephen and Bonneau, Richard and AlQuraishi, Mohammed},\n  booktitle = {Advances in Neural Information Processing Systems 36: Datasets and Benchmarks Track},\n  year      = {2023},\n  url       = {https://openreview.net/forum?id=gO0kS0eE0F},\n  eprint    = {2308.05326},\n  archivePrefix = {arXiv},\n  primaryClass  = {q-bio.BM}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "51c68d368741c428b2baac9d024f705ccd372a82",
 "stated_evidence": "https://huggingface.co/datasets/LiteFold/OpenProteinSet/blob/51c68d368741c428b2baac9d024f705ccd372a82/README.md",
 "file_evidence": "https://huggingface.co/datasets/LiteFold/OpenProteinSet/tree/51c68d368741c428b2baac9d024f705ccd372a82",
 "card_nc": false
}