{"as_of":"2026-08-05T10:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f2e1c7ab39674176c3f2ff4ba82ca3ba4ccba119149c66159e519a418221fa4","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":"2026-08-05T06:32:48.257954+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":"2026-06-28T17:38:50.313305Z","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":"2026-07-01T20:56:13.459331Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.03746","last_updated":"2025-03-05T18:58:44Z","snapshot_observed_at":"2026-07-06T20:47:23.647914Z","submitted_at":"2025-03-05T18:58:44Z","title":"Process-based Self-Rewarding Language Models","version":1},"cited_work":{"arxiv_id":"2503.03746","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.03746","snapshot_observed_at":"2026-07-01T20:56:13.459331Z","title":"Process-based self-rewarding language models","venue":null,"work_id":"4472dd48-c3a1-44df-9397-b663f3d2df57","year":2025},"citing_paper":{"arxiv_id":"2509.03526","last_updated":"2026-05-20T03:07:46Z","snapshot_observed_at":"2026-07-06T22:23:05.533901Z","submitted_at":"2025-08-25T07:31:48Z","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-21T22:23:52.392075Z"},"links":{"cited_paper":"/paper/2503.03746","citing_paper":"/paper/2509.03526"},"observation_digest":"sha256:eff5fa9e413ec5969c64753792510eaeb266d14360a95309d290a8ca9f6c35b4","observation_id":"eb21e2a1-3c6e-49e3-8ce8-d505200f1477","resolution":{"observed_at":"2026-05-21T22:24:23.526339Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2503.03746","last_updated":"2025-03-05T18:58:44Z","snapshot_observed_at":"2026-07-06T20:47:23.647914Z","submitted_at":"2025-03-05T18:58:44Z","title":"Process-based Self-Rewarding Language Models","version":1},"cited_work":{"arxiv_id":"2503.03746","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.03746","snapshot_observed_at":"2026-07-01T20:56:13.459331Z","title":"Process-based self-rewarding language models","venue":null,"work_id":"4472dd48-c3a1-44df-9397-b663f3d2df57","year":2025},"citing_paper":{"arxiv_id":"2605.07353","last_updated":"2026-05-08T07:08:25Z","snapshot_observed_at":"2026-07-06T23:19:46.018236Z","submitted_at":"2026-05-08T07:08:25Z","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-11T02:10:40.020460Z"},"links":{"cited_paper":"/paper/2503.03746","citing_paper":"/paper/2605.07353"},"observation_digest":"sha256:9232f9d26290de52c892ee4d937e8598da46077579375f1c3118fa5e5ef3cf31","observation_id":"6a02aacb-5e6a-4cad-b865-ae18588b1717","resolution":{"observed_at":"2026-05-11T03:55:53.875021Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2503.03746","last_updated":"2025-03-05T18:58:44Z","snapshot_observed_at":"2026-07-06T20:47:23.647914Z","submitted_at":"2025-03-05T18:58:44Z","title":"Process-based Self-Rewarding Language Models","version":1},"cited_work":{"arxiv_id":"2503.03746","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.03746","snapshot_observed_at":"2026-07-01T20:56:13.459331Z","title":"Process-based self-rewarding language models","venue":null,"work_id":"4472dd48-c3a1-44df-9397-b663f3d2df57","year":2025},"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":77,"source":"arxiv_source","source_observed_at":"2026-06-28T17:38:50.313305Z"},"links":{"cited_paper":"/paper/2503.03746","citing_paper":"/paper/2606.01249"},"observation_digest":"sha256:bbfe5b196640cedce92969c14fcd0eb2c6e85d20ab9d7b5e52cbcdbe061a41e4","observation_id":"9982bb87-d892-4eb1-a149-e18add8e1e38","resolution":{"observed_at":"2026-07-01T20:56:13.460577Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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/2503.03746/citation-record","integrity":"/paper/2503.03746/integrity","json":"/paper/2503.03746/citation-record.json","paper":"/paper/2503.03746"},"outbound":[],"paper":{"arxiv_id":"2503.03746","last_updated":"2025-03-05T18:58:44Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:47:23.647914Z","submitted_at":"2025-03-05T18:58:44Z","title":"Process-based Self-Rewarding Language Models"},"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 3 inbound Pith citation observations for arXiv:2503.03746."}