{"work":{"id":"6dea6cb7-a4e5-478a-ab3c-eeeb335abd51","openalex_id":null,"doi":null,"arxiv_id":"2604.02288","raw_key":null,"title":"Unifying group-relative and self-distillation policy optimization via sample routing.arXiv preprint arXiv:2604.02288, 2026","authors":null,"authors_text":"Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song, Mao Zheng, Haiyun Guo, Dan Zhang, Jinqiao Wang, and Tat-Seng Chua","year":2026,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2604.02288","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-06-28T19:22:34.483913+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T01:50:51.278831+00:00","updated_at":"2026-06-28T19:22:34.483913+00:00","title_quality_ok":true,"display_title":"Unifying group-relative and self-distillation policy optimization via sample routing","render_title":"Unifying group-relative and self-distillation policy optimization via sample routing"},"hub":{"state":{"work_id":"6dea6cb7-a4e5-478a-ab3c-eeeb335abd51","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":12,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2026-04-14T17:54:28+00:00","last_pith_cited_at":"2026-05-30T00:05:14+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":"2026-06-30T07:09:34.500439+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":6}],"polarity_counts":[{"context_polarity":"background","n":6}],"runs":{},"summary":{},"graph":{},"authors":[]}}