{"work":{"id":"2881a661-1c4c-4e66-abba-aa3a176aadff","openalex_id":null,"doi":null,"arxiv_id":"2512.01374","raw_key":null,"title":"Stabilizing reinforcement learning with llms: Formulation and practices.arXiv preprint arXiv:2512.01374, 2025a","authors":null,"authors_text":"Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li, Huiqiang Jiang, Junrong Lin, Yuqiong Liu, Hao Lin, Chencan Wu, Feng Hu, et al","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2512.01374","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-03T16:48:39.913120+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T05:45:22.149006+00:00","updated_at":"2026-07-03T16:48:39.913120+00:00","title_quality_ok":true,"display_title":"Stabilizing reinforcement learning with llms: Formulation and practices.arXiv preprint arXiv:2512.01374, 2025a","render_title":"Stabilizing reinforcement learning with llms: Formulation and practices.arXiv preprint arXiv:2512.01374, 2025a"},"hub":{"state":{"work_id":"2881a661-1c4c-4e66-abba-aa3a176aadff","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":19,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-10-29T08:07:47+00:00","last_pith_cited_at":"2026-06-12T13:44:48+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":"2026-08-21T22:39:47.007044+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}