{"as_of":"2026-08-05T01:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0000230bd4662ff5ee319cc045d01de9daa176f4eb5926f6ddda44dab46e7d7","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T22:48:54.238767Z","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":"2026-05-20T22:49:10.147174Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.16155","last_updated":"2023-09-28T04:05:13Z","snapshot_observed_at":"2026-08-02T03:33:25.183604Z","submitted_at":"2023-09-28T04:05:13Z","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","version":1},"cited_work":{"arxiv_id":"2309.16155","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.16155","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The trickle-down impact of reward (in-) consistency on rlhf","venue":null,"work_id":"da4b2d29-513d-4425-88fe-306a0ee15978","year":2023},"citing_paper":{"arxiv_id":"2605.16339","last_updated":"2026-05-07T16:48:48Z","snapshot_observed_at":"2026-07-06T23:27:29.931962Z","submitted_at":"2026-05-07T16:48:48Z","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-20T22:48:54.238767Z"},"links":{"cited_paper":"/paper/2309.16155","citing_paper":"/paper/2605.16339"},"observation_digest":"sha256:6ac0d6212b413f2f4ce1ad9dcceff8d8cac36ca8df29ecdec448849cf8c1ba33","observation_id":"3e6f5d60-88fa-49db-976c-c9de20bdec60","resolution":{"observed_at":"2026-05-20T22:49:10.149538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.16155/citation-record","integrity":"/paper/2309.16155/integrity","json":"/paper/2309.16155/citation-record.json","paper":"/paper/2309.16155"},"outbound":[],"paper":{"arxiv_id":"2309.16155","last_updated":"2023-09-28T04:05:13Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-02T03:33:25.183604Z","submitted_at":"2023-09-28T04:05:13Z","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2309.16155."}