{"as_of":"2026-08-09T16:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:984ed1a62ce9a4b024df8fbfd57e5569ad17f2c589807dc7235f210fad17b146","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":"2026-08-09T06:31:02.800959+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":"2026-08-09T14:54:29.303558Z","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":"2026-05-24T01:18:42.172952Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.08589","last_updated":"2023-11-08T18:10:10Z","snapshot_observed_at":"2026-08-05T19:09:04.764238Z","submitted_at":"2023-09-15T17:44:17Z","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","version":2},"cited_work":{"arxiv_id":"2309.08589","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.08589","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a9d2c87f-c13e-40de-8073-aba490b2b092","year":2023},"citing_paper":{"arxiv_id":"2405.02079","last_updated":"2025-04-18T11:20:24Z","snapshot_observed_at":"2026-08-03T06:11:43.529044Z","submitted_at":"2024-05-03T13:12:28Z","title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-24T01:17:26.111194Z"},"links":{"cited_paper":"/paper/2309.08589","citing_paper":"/paper/2405.02079"},"observation_digest":"sha256:71347bff8984b8951e8e11af9e27a443b9ed2e34a13ac36b1aa786768314b097","observation_id":"7f9b6710-3f08-4f14-8768-c4ac757c7b4f","resolution":{"observed_at":"2026-05-24T01:18:42.175859Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08589","last_updated":"2023-11-08T18:10:10Z","snapshot_observed_at":"2026-08-05T19:09:04.764238Z","submitted_at":"2023-09-15T17:44:17Z","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08589","snapshot_observed_at":"2026-08-09T14:54:29.303558Z","title":"and Parkes, D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01612","last_updated":"2025-02-13T05:32:54Z","snapshot_observed_at":"2026-08-09T14:47:41.525137Z","submitted_at":"2025-02-03T18:45:22Z","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-09T14:54:29.303558Z"},"links":{"cited_paper":"/paper/2309.08589","citing_paper":"/paper/2502.01612"},"observation_digest":"sha256:2d4f932c838316e7d2ef09cf76750310c4848ab90412fb6a582864ad81e1f366","observation_id":"a895ed22-caee-4744-83fa-00bced60297d","resolution":{"observed_at":"2026-08-09T14:54:29.303558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08589","last_updated":"2023-11-08T18:10:10Z","snapshot_observed_at":"2026-08-05T19:09:04.764238Z","submitted_at":"2023-09-15T17:44:17Z","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08589","snapshot_observed_at":"2026-08-08T15:11:08.206499Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06533","last_updated":"2025-02-10T14:56:25Z","snapshot_observed_at":"2026-08-08T15:05:57.951816Z","submitted_at":"2025-02-10T14:56:25Z","title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T15:11:08.206499Z"},"links":{"cited_paper":"/paper/2309.08589","citing_paper":"/paper/2502.06533"},"observation_digest":"sha256:a05d6d73d5141f570d521ec1bea6ac76bbc7f94f6c95065b3ff4bff4a87be55c","observation_id":"18beb684-bb45-4677-b7c7-b82c595574a7","resolution":{"observed_at":"2026-08-08T15:11:08.206499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.08589/citation-record","integrity":"/paper/2309.08589/integrity","json":"/paper/2309.08589/citation-record.json","paper":"/paper/2309.08589"},"outbound":[],"paper":{"arxiv_id":"2309.08589","last_updated":"2023-11-08T18:10:10Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T19:09:04.764238Z","submitted_at":"2023-09-15T17:44:17Z","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator"},"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 3 inbound Pith citation observations for arXiv:2309.08589."}