{"work":{"id":"c77a7cf8-1b17-4b88-9704-46dee2f8ca0f","openalex_id":null,"doi":null,"arxiv_id":"2312.14925","raw_key":null,"title":"A survey of reinforcement learning from human feedback","authors":null,"authors_text":"Kaufmann, T","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2312.14925","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-06-29T00:02:49.995380+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T00:25:50.016183+00:00","updated_at":"2026-06-29T00:02:49.995380+00:00","title_quality_ok":true,"display_title":"A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925","render_title":"A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925"},"hub":{"state":{"work_id":"c77a7cf8-1b17-4b88-9704-46dee2f8ca0f","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":13,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2024-09-28T06:20:03+00:00","last_pith_cited_at":"2026-05-29T03:25:56+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":"2026-06-29T16:09:05.206752+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}