{"work":{"id":"fae7d2ce-42fc-469f-9b46-42b5103f2013","openalex_id":null,"doi":null,"arxiv_id":"2512.16649","raw_key":null,"title":"Rewarding the unlikely: Lifting grpo beyond distribu- tion sharpening","authors":null,"authors_text":"Andre Wang He, Daniel Fried, and Sean Welleck","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2512.16649","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T00:29:16.481302+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T11:11:06.783802+00:00","updated_at":"2026-07-04T00:29:16.481302+00:00","title_quality_ok":true,"display_title":"Justrl: Scaling a 1.5 b llm with a simple rl recipe","render_title":"Justrl: Scaling a 1.5 b llm with a simple rl recipe"},"hub":{"state":{"work_id":"fae7d2ce-42fc-469f-9b46-42b5103f2013","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":"2026-01-12T10:14:09+00:00","last_pith_cited_at":"2026-06-17T16:13:42+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":"2026-07-04T13:56:50.604100+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}