{
 "id": "evaleval/auto-benchmarkcards",
 "owner": "evaleval",
 "name": "auto-benchmarkcards",
 "downloads": 421,
 "likes": 4,
 "last_modified": "2026-07-14T13:24:47.000Z",
 "stated_licence": "cdla-permissive-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "If you use this dataset, please cite the Auto-BenchmarkCard paper:\n\n- A. Hofmann, I. Vejsbjerg, D. Salwala, and E. M. Daly, \"Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation,\" 2025, arXiv:2512.09577.\n\nThis dataset's pipeline also builds on:\n\n- A. Sokol et al., \"BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks,\" 2024, arXiv:2410.12974.\n- R. Marinescu et al., \"FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models,\" 2025, arXiv:2502.18573.\n- F. Bagehorn et al., \"AI Risk Atlas: Taxonomy and Tooling for Navigating AI Risks and Resources,\" 2025, arXiv:2503.05780.\n- E. Bandel et al., \"Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI,\" 2024, arXiv:2401.14019.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "0a86cea5b55d6070bd7f1f020f01281e1631adba",
 "stated_evidence": "https://huggingface.co/datasets/evaleval/auto-benchmarkcards/blob/0a86cea5b55d6070bd7f1f020f01281e1631adba/README.md",
 "file_evidence": "https://huggingface.co/datasets/evaleval/auto-benchmarkcards/tree/0a86cea5b55d6070bd7f1f020f01281e1631adba",
 "card_nc": false
}