{"as_of":"2026-08-07T22:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0944d116cbeab5704573176eca120d0b67326d36bf489deb4f09bd1e9d8c9a20","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:47:20.823057Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T13:49:14.654740Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.10584","last_updated":"2024-02-25T19:15:26Z","snapshot_observed_at":"2026-07-06T17:04:09.326801Z","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10584","snapshot_observed_at":"2026-08-07T05:47:20.823057Z","title":"Policy optimization in rlhf: The impact of out-of-preference data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07035","last_updated":"2025-06-08T07:59:09Z","snapshot_observed_at":"2026-08-07T05:41:12.179171Z","submitted_at":"2025-06-08T07:59:09Z","title":"AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:20.823057Z"},"links":{"cited_paper":"/paper/2312.10584","citing_paper":"/paper/2506.07035"},"observation_digest":"sha256:6e2948477ed9f5fde3a6cba6c9c4c91e215d6f82f439648d65364d44a33f0a0b","observation_id":"cbcaa8fe-2360-4a59-8d31-ee40a228821a","resolution":{"observed_at":"2026-08-07T05:47:20.823057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10584","last_updated":"2024-02-25T19:15:26Z","snapshot_observed_at":"2026-07-06T17:04:09.326801Z","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10584","snapshot_observed_at":"2026-08-07T05:40:17.937230Z","title":"Policy optimization in rlhf: The impact of out-of-preference data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07492","last_updated":"2025-06-09T07:11:01Z","snapshot_observed_at":"2026-08-07T05:29:54.015791Z","submitted_at":"2025-06-09T07:11:01Z","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T05:40:17.937230Z"},"links":{"cited_paper":"/paper/2312.10584","citing_paper":"/paper/2506.07492"},"observation_digest":"sha256:b36bfc9b5d39e26196501d0a5bf2c46c1e778f9d57113366accd3af37ec4bd3b","observation_id":"b7c6d022-71b5-42c7-90d9-c7b5bcbd23f7","resolution":{"observed_at":"2026-08-07T05:40:17.937230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10584","last_updated":"2024-02-25T19:15:26Z","snapshot_observed_at":"2026-07-06T17:04:09.326801Z","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10584","snapshot_observed_at":"2026-08-07T01:04:31.048119Z","title":"Policy optimization in rlhf: The impact of out-of-preference data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12350","last_updated":"2025-06-14T05:14:49Z","snapshot_observed_at":"2026-08-07T00:49:43.707111Z","submitted_at":"2025-06-14T05:14:49Z","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T01:04:31.048119Z"},"links":{"cited_paper":"/paper/2312.10584","citing_paper":"/paper/2506.12350"},"observation_digest":"sha256:4dbd56b41563f82e1bb6a62208c8d1b8235f36fa487436dd981c326f9ac187e5","observation_id":"37cfa10b-53f2-4d10-807e-fffd6a485e01","resolution":{"observed_at":"2026-08-07T01:04:31.048119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10584","last_updated":"2024-02-25T19:15:26Z","snapshot_observed_at":"2026-07-06T17:04:09.326801Z","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","version":2},"cited_work":{"arxiv_id":"2312.10584","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.10584","snapshot_observed_at":"2026-08-06T13:49:14.654740Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","venue":"cs.LG","work_id":"a61fb487-8a71-4c69-8aa3-3e2b8ba799fb","year":2023},"citing_paper":{"arxiv_id":"2507.20181","last_updated":"2025-07-27T08:55:40Z","snapshot_observed_at":"2026-08-06T13:49:07.681314Z","submitted_at":"2025-07-27T08:55:40Z","title":"SGPO: Self-Generated Preference Optimization based on Self-Improver","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T13:49:10.944764Z"},"links":{"cited_paper":"/paper/2312.10584","citing_paper":"/paper/2507.20181"},"observation_digest":"sha256:37cb4bace1f9cb0f9b2cb2800088277653fb875bc6106026b0a44d6577378315","observation_id":"6c8d9209-bf45-4f0c-b311-fe1ce12383eb","resolution":{"observed_at":"2026-08-06T13:49:14.825066Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.10584/citation-record","integrity":"/paper/2312.10584/integrity","json":"/paper/2312.10584/citation-record.json","paper":"/paper/2312.10584"},"outbound":[],"paper":{"arxiv_id":"2312.10584","last_updated":"2024-02-25T19:15:26Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:04:09.326801Z","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2312.10584."}