{"as_of":"2026-08-05T02:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:28898711216ca24c93759d24298c2fe22c5d7aa7fa0db37474770b8232bcd8de","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":"2026-06-28T17:38:50.313305Z","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":"2026-07-01T20:56:13.607768Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.21645","last_updated":"2025-07-29T10:02:43Z","snapshot_observed_at":"2026-07-06T22:04:30.930113Z","submitted_at":"2025-07-29T10:02:43Z","title":"Libra: Assessing and Improving Reward Model by Learning to Think","version":1},"cited_work":{"arxiv_id":"2507.21645","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21645","snapshot_observed_at":"2026-07-01T20:56:13.607768Z","title":"arXiv preprint arXiv:2507.21645 , year =","venue":null,"work_id":"f46cc257-ff46-4b66-8859-06680a278c07","year":null},"citing_paper":{"arxiv_id":"2606.01249","last_updated":"2026-06-17T04:44:10Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-31T14:04:51Z","title":"Trust Region On-Policy Distillation","version":3},"reference_index":160,"source":"arxiv_source","source_observed_at":"2026-06-28T17:38:50.313305Z"},"links":{"cited_paper":"/paper/2507.21645","citing_paper":"/paper/2606.01249"},"observation_digest":"sha256:7c7d7915e95da84f938b46ffe91fce470227f46edc16c95e865e43b08a2cada5","observation_id":"eeeec852-76d3-4852-baaa-b941d4b038e3","resolution":{"observed_at":"2026-07-01T20:56:13.609324Z","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/2507.21645/citation-record","integrity":"/paper/2507.21645/integrity","json":"/paper/2507.21645/citation-record.json","paper":"/paper/2507.21645"},"outbound":[],"paper":{"arxiv_id":"2507.21645","last_updated":"2025-07-29T10:02:43Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T22:04:30.930113Z","submitted_at":"2025-07-29T10:02:43Z","title":"Libra: Assessing and Improving Reward Model by Learning to Think"},"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:2507.21645."}