{"as_of":"2026-08-15T12:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1bd657a2c61a55d58d39bd643611a56a3023d747cbf95f037a05916ea46cc5b2","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T16:30:09.324217Z","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":"2026-08-07T21:36:33.816228Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.07046","last_updated":"2023-03-13T12:13:16Z","snapshot_observed_at":"2026-08-13T12:25:49.303897Z","submitted_at":"2023-03-13T12:13:16Z","title":"Deploying Offline Reinforcement Learning with Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.07046","snapshot_observed_at":"2026-08-12T16:30:09.324217Z","title":"Deploying offline reinforcement learning with human feedback","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","snapshot_observed_at":"2026-08-14T17:35:57.704748Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T16:30:09.324217Z"},"links":{"cited_paper":"/paper/2303.07046","citing_paper":"/paper/2411.13410"},"observation_digest":"sha256:a4ea2169f76ce4612ec8d4c4961b71a07e4a8cb139b64116d4a438b89356d0e3","observation_id":"169bccfd-1b74-4778-ab33-6c0468be2041","resolution":{"observed_at":"2026-08-12T16:30:09.324217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07046","last_updated":"2023-03-13T12:13:16Z","snapshot_observed_at":"2026-08-13T12:25:49.303897Z","submitted_at":"2023-03-13T12:13:16Z","title":"Deploying Offline Reinforcement Learning with Human Feedback","version":1},"cited_work":{"arxiv_id":"2303.07046","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.07046","snapshot_observed_at":"2026-08-07T21:36:33.816228Z","title":"Deploying Offline Reinforcement Learning with Human Feedback","venue":"cs.LG","work_id":"11a939ae-491b-4c49-b566-199f7196b54e","year":2023},"citing_paper":{"arxiv_id":"2502.09417","last_updated":"2025-02-13T15:40:39Z","snapshot_observed_at":"2026-08-15T06:43:43.875296Z","submitted_at":"2025-02-13T15:40:39Z","title":"A Survey of Reinforcement Learning for Optimization in Automation","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-08-07T21:36:33.729197Z"},"links":{"cited_paper":"/paper/2303.07046","citing_paper":"/paper/2502.09417"},"observation_digest":"sha256:01ffa9063118756f9c8736b9fbd9961244fd6108b55d148745d8e78b04b6b0a1","observation_id":"cb1d915b-c4e2-4696-bb63-42d68916a016","resolution":{"observed_at":"2026-08-07T21:36:33.821736Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2303.07046/citation-record","integrity":"/paper/2303.07046/integrity","json":"/paper/2303.07046/citation-record.json","paper":"/paper/2303.07046"},"outbound":[],"paper":{"arxiv_id":"2303.07046","last_updated":"2023-03-13T12:13:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T12:25:49.303897Z","submitted_at":"2023-03-13T12:13:16Z","title":"Deploying Offline Reinforcement Learning with Human Feedback"},"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 2 inbound Pith citation observations for arXiv:2303.07046."}