{
 "id": "zhiminy/EvalEng",
 "owner": "zhiminy",
 "name": "EvalEng",
 "downloads": 87,
 "likes": 5,
 "last_modified": "2026-05-27T04:18:38.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "token-classification",
  "summarization"
 ],
 "citation": "@article{zhao2025evaleng,\n      title={Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild}, \n      author={Zhimin Zhao and Zehao Wang and Abdul Ali Bangash and Bram Adams and Ahmed E. Hassan},\n      year={2026},\n      eprint={2605.24213},\n      archivePrefix={arXiv},\n      primaryClass={cs.SE},\n      url={https://arxiv.org/abs/2605.24213}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "e8bf6d080edfdf47305f27a266b7d7af9d9d96dd",
 "stated_evidence": "https://huggingface.co/datasets/zhiminy/EvalEng/blob/e8bf6d080edfdf47305f27a266b7d7af9d9d96dd/README.md",
 "file_evidence": "https://huggingface.co/datasets/zhiminy/EvalEng/tree/e8bf6d080edfdf47305f27a266b7d7af9d9d96dd",
 "card_nc": false
}