{
 "id": "madrylab/gsm8k-platinum",
 "owner": "madrylab",
 "name": "gsm8k-platinum",
 "downloads": 7715,
 "likes": 48,
 "last_modified": "2025-03-11T14:48:29.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text2text-generation"
 ],
 "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 (mit) is classified as permissive."
}