{"work":{"id":"a63ca98b-8916-47bd-bd9b-d0c693024f4c","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:6ddc5ce808bf62d1d4cff66f","title":"Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017","authors":null,"authors_text":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei","year":2017,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-05-27T02:13:25.495414+00:00","pith_arxiv_id":null,"created_at":"2026-05-12T15:11:39.335339+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30","render_title":"Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30"},"hub":{"state":{"work_id":"a63ca98b-8916-47bd-bd9b-d0c693024f4c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2024-05-20T01:04:40+00:00","last_pith_cited_at":"2026-05-21T17:03:22+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":"2026-06-09T14:55:00.373461+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}