{"as_of":"2026-08-23T12:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:81efd713bbb53ccdd42ad3fde9c2140d3a351618529d24c2154ac3b34df024cd","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T13:24:30.794478Z","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":"2026-05-19T09:52:14.066563Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.00418","last_updated":"2025-06-03T04:43:45Z","snapshot_observed_at":"2026-08-20T23:45:36.381365Z","submitted_at":"2024-11-01T07:29:03Z","title":"Self-Evolved Reward Learning for LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00418","snapshot_observed_at":"2026-08-07T13:24:30.794478Z","title":"Self-evolved reward learning for llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-20T17:24:37.296918Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":106,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.794478Z"},"links":{"cited_paper":"/paper/2411.00418","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6ac27cc37e65edcd9a3170dce7da328849ed32931bd45ce7865725670c6017c1","observation_id":"ad91e8e8-f36a-4406-a439-0057b6e6c276","resolution":{"observed_at":"2026-08-07T13:24:30.794478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00418","last_updated":"2025-06-03T04:43:45Z","snapshot_observed_at":"2026-08-20T23:45:36.381365Z","submitted_at":"2024-11-01T07:29:03Z","title":"Self-Evolved Reward Learning for LLMs","version":3},"cited_work":{"arxiv_id":"2411.00418","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.00418","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-evolved reward learning for llms","venue":null,"work_id":"8e15252a-ef9e-4358-8bc0-22f09fb4c98f","year":null},"citing_paper":{"arxiv_id":"2506.13351","last_updated":"2026-05-07T20:19:13Z","snapshot_observed_at":"2026-08-17T13:08:52.450705Z","submitted_at":"2025-06-16T10:43:38Z","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T09:48:56.990745Z"},"links":{"cited_paper":"/paper/2411.00418","citing_paper":"/paper/2506.13351"},"observation_digest":"sha256:6bb99f07d02681f04aa53f1c567a9f9c4026834613011ccfdefbda037233b5ab","observation_id":"27fc0b52-f5ff-4bdb-a168-adbcd38d5fa2","resolution":{"observed_at":"2026-05-19T09:52:14.068048Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.00418/citation-record","integrity":"/paper/2411.00418/integrity","json":"/paper/2411.00418/citation-record.json","paper":"/paper/2411.00418"},"outbound":[],"paper":{"arxiv_id":"2411.00418","last_updated":"2025-06-03T04:43:45Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-20T23:45:36.381365Z","submitted_at":"2024-11-01T07:29:03Z","title":"Self-Evolved Reward Learning for LLMs"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.00418."}