{"as_of":"2026-08-07T18:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:08c7250d3c49190839ea1f43ffe6489264bc04e6ba35c39429b222a13d672f34","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T05:40:17.910923Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.18742","last_updated":"2024-08-06T22:33:26Z","snapshot_observed_at":"2026-07-06T17:52:05.486230Z","submitted_at":"2024-03-27T16:39:28Z","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18742","snapshot_observed_at":"2026-08-07T05:40:17.910923Z","title":"and Li, Y","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":25,"source":"arxiv_source","source_observed_at":"2026-08-07T05:40:17.910923Z"},"links":{"cited_paper":"/paper/2403.18742","citing_paper":"/paper/2506.07492"},"observation_digest":"sha256:141347132d9b0ce1e1d48f2a38a4fd0166d2d4e8f5e889b2e386075d9dd51eff","observation_id":"e1a6ffa6-1c87-438c-9b8e-5c3b6a11a067","resolution":{"observed_at":"2026-08-07T05:40:17.910923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18742","last_updated":"2024-08-06T22:33:26Z","snapshot_observed_at":"2026-07-06T17:52:05.486230Z","submitted_at":"2024-03-27T16:39:28Z","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","version":5},"cited_work":{"arxiv_id":"2403.18742","doi":"10.48550/arxiv.2403.18742","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Understanding the","venue":"arXiv (Cornell University)","work_id":"93599c7c-039d-4a37-bca5-4ef09c469019","year":null},"citing_paper":{"arxiv_id":"2606.02211","last_updated":"2026-06-01T13:10:49Z","snapshot_observed_at":"2026-08-02T18:41:16.377453Z","submitted_at":"2026-06-01T13:10:49Z","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","version":1},"reference_index":109,"source":"arxiv_source","source_observed_at":"2026-06-28T14:25:43.147442Z"},"links":{"cited_paper":"/paper/2403.18742","citing_paper":"/paper/2606.02211"},"observation_digest":"sha256:b7164c300ed27b21387f6b817d7d77951c678f6f2b67ebecb667de00c4d2d866","observation_id":"14d53ddd-c376-4aa8-9dfd-089bdfb54471","resolution":{"observed_at":"2026-06-28T14:32:18.167653Z","resolver_source":"arxiv_id","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/2403.18742/citation-record","integrity":"/paper/2403.18742/integrity","json":"/paper/2403.18742/citation-record.json","paper":"/paper/2403.18742"},"outbound":[],"paper":{"arxiv_id":"2403.18742","last_updated":"2024-08-06T22:33:26Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:52:05.486230Z","submitted_at":"2024-03-27T16:39:28Z","title":"Understanding the Learning Dynamics of Alignment with Human Feedback"},"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 2 inbound Pith citation observations for arXiv:2403.18742."}