{
 "id": "NiniCat/MMLU-SR",
 "owner": "NiniCat",
 "name": "MMLU-SR",
 "downloads": 1554,
 "likes": 2,
 "last_modified": "2025-05-15T06:42:06.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "mmlu",
   "licence": null,
   "found": false,
   "evidence": "https://huggingface.co/datasets/mmlu"
  }
 ],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "If you use this datasets in your work, please cite it as follows:\n```bib\n@misc{wang2024mmlusrbenchmarkstresstestingreasoning,\n      title={MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models}, \n      author={Wentian Wang and Sarthak Jain and Paul Kantor and Jacob Feldman and Lazaros Gallos and Hao Wang},\n      year={2024},\n      eprint={2406.15468},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2406.15468}, \n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID for at least one declared source dataset.",
 "revision": "2c0b9096737078969a0af2b548e0f7682271fff1",
 "stated_evidence": "https://huggingface.co/datasets/NiniCat/MMLU-SR/blob/2c0b9096737078969a0af2b548e0f7682271fff1/README.md",
 "file_evidence": "https://huggingface.co/datasets/NiniCat/MMLU-SR/tree/2c0b9096737078969a0af2b548e0f7682271fff1",
 "card_nc": false
}