{"work":{"id":"df9d34f5-d155-448e-bc2f-616fd5e25e85","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:02c0aeeb504c406b8c9f97d5","title":"Direct preference optimization: Your language model is secretly a reward model,","authors":null,"authors_text":"R","year":2023,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-21T21:44:23.613295+00:00","pith_arxiv_id":null,"created_at":"2026-05-14T08:05:37.355887+00:00","updated_at":"2026-05-21T21:44:23.613295+00:00","title_quality_ok":true,"display_title":"Direct preference optimization: Your language model is secretly a reward model","render_title":"Direct preference optimization: Your language model is secretly a reward model"},"hub":{"state":{"work_id":"df9d34f5-d155-448e-bc2f-616fd5e25e85","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2025-10-14T16:44:39+00:00","last_pith_cited_at":"2026-05-09T11:43:47+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":"2026-05-26T13:16:33.316020+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}