{"work":{"id":"9d5b91f5-dd34-4c04-925b-ae80101224d5","openalex_id":null,"doi":null,"arxiv_id":"2405.00675","raw_key":null,"title":"Self-play preference optimization for language model alignment.arXiv preprint arXiv:2405.00675,","authors":null,"authors_text":"Yue Wu, Zhiqing Sun, Huizhuo Yuan, Kaixuan Ji, Yiming Yang, and Quanquan Gu","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2405.00675","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-06-29T12:33:24.372431+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:20:41.739278+00:00","updated_at":"2026-06-29T12:33:24.372431+00:00","title_quality_ok":true,"display_title":"Jing Xu, Andrew Lee, Sainbayar Sukhbaatar, and Jason Weston","render_title":"Jing Xu, Andrew Lee, Sainbayar Sukhbaatar, and Jason Weston"},"hub":{"state":{"work_id":"9d5b91f5-dd34-4c04-925b-ae80101224d5","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2024-08-27T18:04:07+00:00","last_pith_cited_at":"2026-05-28T05:47:40+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":"2026-06-29T16:49:06.356508+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}