{"work":{"id":"efe39feb-3afa-48ed-9725-593906f19aac","openalex_id":null,"doi":null,"arxiv_id":"2503.16219","raw_key":null,"title":"Reinforcement learning for reasoning in small llms: What works and what doesn’t","authors":null,"authors_text":"Quy-Anh Dang and Chris Ngo","year":2026,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2503.16219","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-21T14:10:13.143311+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T11:10:09.650571+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Reinforcement learning for reasoning in small llms: What works and what doesn’t","render_title":"Reinforcement learning for reasoning in small llms: What works and what doesn’t"},"hub":{"state":{"work_id":"efe39feb-3afa-48ed-9725-593906f19aac","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-03-12T17:35:03+00:00","last_pith_cited_at":"2026-05-16T15:16:00+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":"2026-06-06T05:20:23.892481+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}