{"as_of":"2026-08-09T07:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b7b5b55163441bdc8e611a3916a2c7eb3d290391ae370d0f31bc84f892632cb","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:31:46.321451Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T14:02:39.746380Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.13709","last_updated":"2024-08-22T17:56:15Z","snapshot_observed_at":"2026-07-06T18:48:37.723242Z","submitted_at":"2024-07-18T17:08:10Z","title":"Understanding Reference Policies in Direct Preference Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.13709","snapshot_observed_at":"2026-08-07T11:31:46.321451Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.15717","last_updated":"2025-06-03T03:39:29Z","snapshot_observed_at":"2026-08-07T11:22:31.753795Z","submitted_at":"2025-06-03T03:39:29Z","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T11:31:46.321451Z"},"links":{"cited_paper":"/paper/2407.13709","citing_paper":"/paper/2506.15717"},"observation_digest":"sha256:14fa43eb0d94fbe306017ddde613c82e6d4e518a55c2e7d73bfa8e57bd9a2cd3","observation_id":"f08a6236-93fc-4552-8dd3-bd05dca68fbf","resolution":{"observed_at":"2026-08-07T11:31:46.321451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13709","last_updated":"2024-08-22T17:56:15Z","snapshot_observed_at":"2026-07-06T18:48:37.723242Z","submitted_at":"2024-07-18T17:08:10Z","title":"Understanding Reference Policies in Direct Preference Optimization","version":2},"cited_work":{"arxiv_id":"2407.13709","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.13709","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Understanding reference policies in direct preference optimization","venue":null,"work_id":"a094d60a-890c-4b07-83ae-c3e62edf4e00","year":2024},"citing_paper":{"arxiv_id":"2509.20265","last_updated":"2026-04-29T12:32:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-09-24T15:52:36Z","title":"Failure Modes of Maximum Entropy RLHF","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-18T14:02:11.084514Z"},"links":{"cited_paper":"/paper/2407.13709","citing_paper":"/paper/2509.20265"},"observation_digest":"sha256:a7e3641a44aaa8f19de973e63c1bab7cb5bc93b1cbea5cc9c46a0c5ed591e4d7","observation_id":"6696e1aa-96e1-4e59-8a36-0fe06ff8766c","resolution":{"observed_at":"2026-05-18T14:02:39.752298Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.13709/citation-record","integrity":"/paper/2407.13709/integrity","json":"/paper/2407.13709/citation-record.json","paper":"/paper/2407.13709"},"outbound":[],"paper":{"arxiv_id":"2407.13709","last_updated":"2024-08-22T17:56:15Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:48:37.723242Z","submitted_at":"2024-07-18T17:08:10Z","title":"Understanding Reference Policies in Direct Preference Optimization"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.13709."}