{"as_of":"2026-08-05T08:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e1a3c2867681b297dd7107547afb1a3883f29c3949616fa74af10beebffadf0","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":"2026-08-05T06:32:48.257954+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":"2026-08-02T08:40:51.476948Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.10202","last_updated":"2023-09-18T23:06:32Z","snapshot_observed_at":"2026-07-06T16:20:17.310644Z","submitted_at":"2023-09-18T23:06:32Z","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.10202","snapshot_observed_at":"2026-07-11T13:53:36.775836Z","title":"arXiv preprint arXiv:2309.10202 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":1},"reference_index":166,"source":"arxiv_source","source_observed_at":"2026-07-11T13:53:36.775836Z"},"links":{"cited_paper":"/paper/2309.10202","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:fd2f64ff73d171c6f8bcdc305797101d466ff8e234e8e105d2babe2163ae7eed","observation_id":"6581432e-bbab-4378-a23b-be62c4f63750","resolution":{"observed_at":"2026-07-11T13:53:36.775836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.10202","last_updated":"2023-09-18T23:06:32Z","snapshot_observed_at":"2026-07-06T16:20:17.310644Z","submitted_at":"2023-09-18T23:06:32Z","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.10202","snapshot_observed_at":"2026-08-02T08:40:51.476948Z","title":"arXiv preprint arXiv:2309.10202 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":3},"reference_index":167,"source":"arxiv_source","source_observed_at":"2026-08-02T08:40:51.476948Z"},"links":{"cited_paper":"/paper/2309.10202","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:a0e101a95c2ec35fdb200277adeea3e256142a9b761880b99db0d8ef2110a25f","observation_id":"0ab92fea-3ac8-442d-be74-8c23962356f6","resolution":{"observed_at":"2026-08-02T08:40:51.476948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.10202/citation-record","integrity":"/paper/2309.10202/integrity","json":"/paper/2309.10202/citation-record.json","paper":"/paper/2309.10202"},"outbound":[],"paper":{"arxiv_id":"2309.10202","last_updated":"2023-09-18T23:06:32Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T16:20:17.310644Z","submitted_at":"2023-09-18T23:06:32Z","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal"},"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 2 inbound Pith citation observations for arXiv:2309.10202."}