{"as_of":"2026-08-05T07:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:597e95137defc1895f5f6a0bb07fa414e3b28fb1fd4af9b2283a3e585c305053","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":"2026-08-05T06:32:48.257954+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":"2026-05-13T06:07:56.678339Z","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":"2026-05-13T06:07:56.734008Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.20850","last_updated":"2024-10-18T15:43:02Z","snapshot_observed_at":"2026-07-06T18:23:19.450809Z","submitted_at":"2024-05-31T14:33:07Z","title":"Improving Reward Models with Synthetic Critiques","version":2},"cited_work":{"arxiv_id":"2405.20850","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.20850","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"0fa79093-ac5d-4567-b8a0-29823b54aba6","year":2024},"citing_paper":{"arxiv_id":"2507.17746","last_updated":"2025-10-03T01:55:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-23T17:57:55Z","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-13T06:07:56.678339Z"},"links":{"cited_paper":"/paper/2405.20850","citing_paper":"/paper/2507.17746"},"observation_digest":"sha256:c65f7a9e6fba06957c7449f0ad284a5b6c6bbe1fd9c89051bb26a5d592fb7edb","observation_id":"6033c67d-e2d2-4948-892c-2582aa79a115","resolution":{"observed_at":"2026-05-13T06:07:56.735973Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.20850/citation-record","integrity":"/paper/2405.20850/integrity","json":"/paper/2405.20850/citation-record.json","paper":"/paper/2405.20850"},"outbound":[],"paper":{"arxiv_id":"2405.20850","last_updated":"2024-10-18T15:43:02Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:23:19.450809Z","submitted_at":"2024-05-31T14:33:07Z","title":"Improving Reward Models with Synthetic Critiques"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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:2405.20850."}