{
 "id": "owl-owl/POVBench",
 "owner": "owl-owl",
 "name": "POVBench",
 "downloads": 2551,
 "likes": 0,
 "last_modified": "2026-09-06T17:19:18.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering",
  "image-text-to-text"
 ],
 "citation": "@inproceedings{shirasaka2026povbench,\n  title     = {Contextual Observer Grounding: Evaluating Situated Spatial\n               Reasoning in Vision-Language Models},\n  author    = {Shirasaka, Mimo and Zhang, Haochen and Bisk, Yonatan},\n  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},\n  year      = {2026}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "fbaf9d7abdbeb1c19f98fce3076d3ad51f14e8b1",
 "stated_evidence": "https://huggingface.co/datasets/owl-owl/POVBench/blob/fbaf9d7abdbeb1c19f98fce3076d3ad51f14e8b1/README.md",
 "file_evidence": "https://huggingface.co/datasets/owl-owl/POVBench/blob/fbaf9d7abdbeb1c19f98fce3076d3ad51f14e8b1/LICENSE",
 "card_nc": false
}