{"as_of":"2026-08-15T09:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:873b2369cbb4131581d0236c54048b87f12bcf8ab20231d6713d61630fc77779","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T12:00:48.944312Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T12:00:49.442820Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.10202","last_updated":"2023-09-18T23:06:32Z","snapshot_observed_at":"2026-08-13T10:10:26.519402Z","submitted_at":"2023-09-18T23:06:32Z","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","version":1},"cited_work":{"arxiv_id":"2309.10202","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.10202","snapshot_observed_at":"2026-08-07T12:00:49.442820Z","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","venue":"cs.CL","work_id":"3b2f45af-b695-4724-969f-0a0526f7709e","year":2023},"citing_paper":{"arxiv_id":"2506.00805","last_updated":"2025-06-01T03:11:00Z","snapshot_observed_at":"2026-08-13T07:30:38.504171Z","submitted_at":"2025-06-01T03:11:00Z","title":"HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T12:00:48.944312Z"},"links":{"cited_paper":"/paper/2309.10202","citing_paper":"/paper/2506.00805"},"observation_digest":"sha256:893d356da8ebe8de0532eb2f99b24cba3f04d1fef32563855d4f9e7503e3ce9d","observation_id":"74fcdd41-16a4-44ad-9e58-5ebebc2616c1","resolution":{"observed_at":"2026-08-07T12:00:49.448506Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.10202","last_updated":"2023-09-18T23:06:32Z","snapshot_observed_at":"2026-08-13T10:10:26.519402Z","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":"sha256:9bb51f2a49846208b440232c9b5f69f07936ec8451a8ed9716450bab7bb2b148","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":"2026-08-13T10:10:26.519402Z","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":"sha256:70a671b3e75135f36b13c2fa13e7e6d16b4a5805452c1e38c233a6513aebfa7c","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":"2026-08-13T10:10:26.519402Z","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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2309.10202."}