{"as_of":"2026-08-09T13:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8135f2d75cec4497e078d171ded75e876639827b98d166c61b4e209b12ce5201","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":"2026-08-07T15:09:54.077941Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20850","snapshot_observed_at":"2026-08-07T15:09:54.077941Z","title":"Improving reward models with synthetic critiques.arXiv preprint arXiv:2405.20850, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16265","last_updated":"2025-05-22T05:56:11Z","snapshot_observed_at":"2026-08-07T15:02:24.736790Z","submitted_at":"2025-05-22T05:56:11Z","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:54.077941Z"},"links":{"cited_paper":"/paper/2405.20850","citing_paper":"/paper/2505.16265"},"observation_digest":"sha256:ae4a417196967cdc97d352c912c907bf588ee6d7b00f9324a0d7b7de15f6f115","observation_id":"aa3293c5-7248-418f-b6d0-259228f7611e","resolution":{"observed_at":"2026-08-07T15:09:54.077941Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"sha256:8c2b1f93d6e76cf535f6416a5146486f13fb96a625b190ab03b9169ce73adc23","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 2026-08-09T06:31:02.800959+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":"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20850","snapshot_observed_at":"2026-08-06T14:35:46.596042Z","title":"Improving reward models with synthetic critiques","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18618","last_updated":"2025-07-24T17:54:44Z","snapshot_observed_at":"2026-08-06T14:35:45.675821Z","submitted_at":"2025-07-24T17:54:44Z","title":"TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T14:35:46.596042Z"},"links":{"cited_paper":"/paper/2405.20850","citing_paper":"/paper/2507.18618"},"observation_digest":"sha256:9c522a53f699855772950f6b7fdfc32e7be639fa2f0b180e32235f0fbdbe96c2","observation_id":"666e019f-72e8-4a95-9c53-e87a7e1cefd1","resolution":{"observed_at":"2026-08-06T14:35:46.596042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"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":"2026-08-09T06:31:02.800959+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:2405.20850."}