{
 "id": "arvindcr4/tinker-rl-bench-wandb",
 "owner": "arvindcr4",
 "name": "tinker-rl-bench-wandb",
 "downloads": 92,
 "likes": 0,
 "last_modified": "2026-04-19T15:58:33.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "reinforcement-learning"
 ],
 "citation": "@misc{tinkerrlbench2026,\n  title   = {A Unified Benchmark for RL Post-Training of Language Models},\n  author  = {Arvind, C. R. and Jeyaraj, Sandhya},\n  year    = {2026},\n  note    = {NeurIPS submission, see https://github.com/pes-llm-research/tinker-rl-lab}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "515358206984345b882fce90b3800751d05ffe10",
 "stated_evidence": "https://huggingface.co/datasets/arvindcr4/tinker-rl-bench-wandb/blob/515358206984345b882fce90b3800751d05ffe10/README.md",
 "file_evidence": "https://huggingface.co/datasets/arvindcr4/tinker-rl-bench-wandb/tree/515358206984345b882fce90b3800751d05ffe10",
 "card_nc": false
}