{"work":{"id":"c337a3f9-8f7e-4f6a-b463-5f4193cee20b","openalex_id":null,"doi":null,"arxiv_id":"2508.04349","raw_key":null,"title":"Gtpo and grpo-s: Token and sequence-level reward shaping with policy entropy.arXiv preprint arXiv:2508.04349, 2025","authors":null,"authors_text":"Hongze Tan, Zihan Wang, Jianfei Pan, Jinghao Lin, Hao Wang, Yifan Wu, Tao Chen, Zhihang Zheng, Zhihao Tang, and Haihua Yang","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2508.04349","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-10T14:27:07.358056+00:00","pith_arxiv_id":null,"created_at":"2026-05-12T03:26:19.305038+00:00","updated_at":"2026-07-10T14:27:07.358056+00:00","title_quality_ok":true,"display_title":"Gtpo and grpo-s: Token and sequence-level reward shaping with policy entropy.arXiv preprint arXiv:2508.04349","render_title":"Gtpo and grpo-s: Token and sequence-level reward shaping with policy entropy.arXiv preprint arXiv:2508.04349"},"hub":{"state":{"work_id":"c337a3f9-8f7e-4f6a-b463-5f4193cee20b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-10-11T10:17:38+00:00","last_pith_cited_at":"2026-07-08T23:00:54+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-20T03:00:03.267766+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}