{"as_of":"2026-08-10T16:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d13a8a284306aedbac2a260e6526db25db592423dafcc9c84f7d6e7702c03aa4","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:18:19.155285Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16155","snapshot_observed_at":"2026-08-10T15:18:19.155285Z","title":"The trickle-down impact of reward (in-) consistency on rlhf","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14294","last_updated":"2025-03-02T06:49:21Z","snapshot_observed_at":"2026-08-10T15:12:35.412010Z","submitted_at":"2025-01-24T07:24:23Z","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T15:18:19.155285Z"},"links":{"cited_paper":"/paper/2309.16155","citing_paper":"/paper/2501.14294"},"observation_digest":"sha256:55617a99420e7ee9f2261aa5989eb6766026195ce8f345b450d3b8c1bccc3350","observation_id":"61ba8be3-a380-4ef1-91ff-3978edb02489","resolution":{"observed_at":"2026-08-10T15:18:19.155285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16155","snapshot_observed_at":"2026-08-06T17:48:07.188338Z","title":"The trickle-down impact of reward (in-)consistency on rlhf, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09973","last_updated":"2025-07-14T06:43:00Z","snapshot_observed_at":"2026-08-08T02:31:23.778902Z","submitted_at":"2025-07-14T06:43:00Z","title":"Tiny Reward Models","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T17:48:07.188338Z"},"links":{"cited_paper":"/paper/2309.16155","citing_paper":"/paper/2507.09973"},"observation_digest":"sha256:6043caa7a5e6686246c5f8844de825ca5dab682ae84754a84a25fd3c8a9c3dfc","observation_id":"2237a1c5-ba21-4367-b8f6-dc294cd7fbbc","resolution":{"observed_at":"2026-08-06T17:48:07.188338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"sha256:2947bfc6d75946adccba9f14c52006cb5b96acdba9e32e6cee0743634623f030","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 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2309.16155."}