{"work":{"id":"997bca21-08ad-4445-841f-1609abeb4657","openalex_id":null,"doi":null,"arxiv_id":"2510.07284","raw_key":null,"title":"Nils Reimers and Iryna Gurevych","authors":null,"authors_text":"Direct preference optimization: Your language model is secretly a reward model","year":2019,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2510.07284","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T09:49:44.762854+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T09:56:00.882744+00:00","updated_at":"2026-07-04T09:49:44.762854+00:00","title_quality_ok":true,"display_title":"Online rubrics elicitation from pairwise comparisons","render_title":"Online rubrics elicitation from pairwise comparisons"},"hub":{"state":{"work_id":"997bca21-08ad-4445-841f-1609abeb4657","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2026-03-04T04:18:39+00:00","last_pith_cited_at":"2026-06-22T08:46:23+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":"2026-07-08T08:32:12.102247+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}