{
 "id": "ob11/VL-PRM300K",
 "owner": "ob11",
 "name": "VL-PRM300K",
 "downloads": 70,
 "likes": 1,
 "last_modified": "2025-10-14T14:49:10.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering",
  "reinforcement-learning"
 ],
 "citation": "@misc{ong2025vlprms,\n      title={Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned}, \n      author={Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi, and Soujanya Poria},\n      year={2025},\n      eprint={2509.23250},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/pdf/2509.23250}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "29436a7cac2916af69939e935113fd29ce9d581d",
 "stated_evidence": "https://huggingface.co/datasets/ob11/VL-PRM300K/blob/29436a7cac2916af69939e935113fd29ce9d581d/README.md",
 "file_evidence": "https://huggingface.co/datasets/ob11/VL-PRM300K/tree/29436a7cac2916af69939e935113fd29ce9d581d",
 "card_nc": false
}