{"work":{"id":"a1dbfba1-b433-4260-abc6-bf28628844b9","openalex_id":"https://openalex.org/W4417051599","doi":"10.48550/arxiv.2503.23829","arxiv_id":"2503.23829","raw_key":null,"title":"arXiv preprint arXiv:2503.23829 (2025) 5 20 J","authors":null,"authors_text":"Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, and Dong Yu","year":2025,"venue":"ArXiv.org","abstract":null,"external_url":"https://arxiv.org/abs/2503.23829","cited_by_count":0,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T19:35:39.077724+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"Crossing the reward bridge: Expanding RL with verifiable rewards across diverse domains","render_title":"Crossing the reward bridge: Expanding RL with verifiable rewards across diverse domains"},"hub":{"state":{"work_id":"a1dbfba1-b433-4260-abc6-bf28628844b9","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":0,"distinct_field_count":5,"first_pith_cited_at":"2025-06-16T10:43:38+00:00","last_pith_cited_at":"2026-07-02T16:40:08+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":"2026-08-21T05:29:37.431748+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}