{
 "id": "skelfresearch/principle-bench",
 "owner": "skelfresearch",
 "name": "principle-bench",
 "downloads": 100,
 "likes": 0,
 "last_modified": "2026-10-01T08:33:45.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{sarkar2026principlebench,\n  title     = {A Four-Axis Trustworthiness Benchmark for\n               LLM-as-Judge in Principle-Based Regulation},\n  author    = {Sarkar, Dipankar},\n  booktitle = {2nd Workshop on Secure and Trustworthy Large Language Models\n               (SeT-LLM @ KDD 2026)},\n  year      = {2026},\n  note      = {Non-archival},\n  eprint    = {2608.14329},\n  archivePrefix = {arXiv},\n  url       = {https://arxiv.org/abs/2608.14329}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "71363f6df1b9598fb1c35a7b56317e6ade8187a6",
 "stated_evidence": "https://huggingface.co/datasets/skelfresearch/principle-bench/blob/71363f6df1b9598fb1c35a7b56317e6ade8187a6/README.md",
 "file_evidence": "https://huggingface.co/datasets/skelfresearch/principle-bench/tree/71363f6df1b9598fb1c35a7b56317e6ade8187a6",
 "card_nc": false
}