{"as_of":"2026-08-10T02:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9f48c4a46bdf57deb28a68e76420230d4c9094a706af2f0ad62c6429e7927114","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T13:24:29.885002Z","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":"2026-08-06T16:38:37.065338Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.19279","last_updated":"2024-03-28T10:02:10Z","snapshot_observed_at":"2026-08-08T13:11:57.462199Z","submitted_at":"2024-03-28T10:02:10Z","title":"Fine-Tuning Language Models with Reward Learning on Policy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19279","snapshot_observed_at":"2026-08-07T13:24:29.885002Z","title":"Fine-tuning language models with reward learning on policy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-09T21:30:35.237559Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.885002Z"},"links":{"cited_paper":"/paper/2403.19279","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:269b700b24daacf988124c096b8a7a8b1082610814eac1aa91f88cba956b5ff9","observation_id":"f0950b69-1412-4337-8094-aad210ce9b44","resolution":{"observed_at":"2026-08-07T13:24:29.885002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19279","last_updated":"2024-03-28T10:02:10Z","snapshot_observed_at":"2026-08-08T13:11:57.462199Z","submitted_at":"2024-03-28T10:02:10Z","title":"Fine-Tuning Language Models with Reward Learning on Policy","version":1},"cited_work":{"arxiv_id":"2403.19279","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.19279","snapshot_observed_at":"2026-08-06T16:38:37.065338Z","title":"Fine-Tuning Language Models with Reward Learning on Policy","venue":"cs.CL","work_id":"2f0b6672-3e93-4e92-9b92-6e38f0308128","year":2024},"citing_paper":{"arxiv_id":"2507.12977","last_updated":"2025-07-17T10:26:06Z","snapshot_observed_at":"2026-08-06T16:31:05.348541Z","submitted_at":"2025-07-17T10:26:06Z","title":"Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T16:38:32.272467Z"},"links":{"cited_paper":"/paper/2403.19279","citing_paper":"/paper/2507.12977"},"observation_digest":"sha256:a4c9734235c084d19f4505be860243d5eb77851239a591653fbd41bbf050dde3","observation_id":"40bb854f-01ac-48bd-aa67-351e05df5eba","resolution":{"observed_at":"2026-08-06T16:38:37.143823Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2403.19279/citation-record","integrity":"/paper/2403.19279/integrity","json":"/paper/2403.19279/citation-record.json","paper":"/paper/2403.19279"},"outbound":[],"paper":{"arxiv_id":"2403.19279","last_updated":"2024-03-28T10:02:10Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T13:11:57.462199Z","submitted_at":"2024-03-28T10:02:10Z","title":"Fine-Tuning Language Models with Reward Learning on Policy"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.19279."}