{"work":{"id":"44673d8e-2cc2-4818-86d3-24bc812aa41c","openalex_id":null,"doi":null,"arxiv_id":"2310.12036","raw_key":null,"title":"A general theoretical paradigm to understand learning from human preferences.arXiv preprint arXiv:2310.12036,","authors":null,"authors_text":"Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, and Rémi Munos","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2310.12036","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T08:11:17.211101+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:20:41.681707+00:00","updated_at":"2026-05-22T08:11:17.211101+00:00","title_quality_ok":true,"display_title":"arXiv preprint arXiv:2310.12036 , year=","render_title":"arXiv preprint arXiv:2310.12036 , year="},"hub":{"state":{"work_id":"44673d8e-2cc2-4818-86d3-24bc812aa41c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2024-03-12T14:34:08+00:00","last_pith_cited_at":"2026-05-21T01:02:41+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":"2026-05-28T21:09:11.169196+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"use_method","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}