{
 "id": "madrylab/platinum-bench",
 "owner": "madrylab",
 "name": "platinum-bench",
 "downloads": 629,
 "likes": 23,
 "last_modified": "2025-04-14T18:27:03.000Z",
 "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": [
  "question-answering"
 ],
 "citation": "@misc{vendrow2025largelanguagemodelbenchmarks,\n      title={Do Large Language Model Benchmarks Test Reliability?}, \n      author={Joshua Vendrow and Edward Vendrow and Sara Beery and Aleksander Madry},\n      year={2025},\n      eprint={2502.03461},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG},\n      url={https://arxiv.org/abs/2502.03461}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "51920a33bfb4620c789729ace14141e87a14969b",
 "stated_evidence": "https://huggingface.co/datasets/madrylab/platinum-bench/blob/51920a33bfb4620c789729ace14141e87a14969b/README.md",
 "file_evidence": "https://huggingface.co/datasets/madrylab/platinum-bench/tree/51920a33bfb4620c789729ace14141e87a14969b",
 "card_nc": false
}