{"as_of":"2026-08-09T13:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c2e64157cf27d74418ea48379020f9385e4f11c21e03b48ca1ac011e27a550f6","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:18:56.424024Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":8,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.11312","last_updated":"2023-02-22T11:49:12Z","snapshot_observed_at":"2026-08-04T08:55:37.127470Z","submitted_at":"2023-02-22T11:49:12Z","title":"Behavior Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11312","snapshot_observed_at":"2026-08-07T15:18:56.424024Z","title":"Behavior proximal policy optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15791","last_updated":"2025-06-02T17:53:20Z","snapshot_observed_at":"2026-08-08T04:54:33.756332Z","submitted_at":"2025-05-21T17:44:37Z","title":"VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:18:56.424024Z"},"links":{"cited_paper":"/paper/2302.11312","citing_paper":"/paper/2505.15791"},"observation_digest":"sha256:68de992859ba2454c2992487d971f0ee36e7b93723b256fc029c59c543296c1f","observation_id":"5068b278-5f7a-45ef-94e6-75e76d93dd16","resolution":{"observed_at":"2026-08-07T15:18:56.424024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11312","last_updated":"2023-02-22T11:49:12Z","snapshot_observed_at":"2026-08-04T08:55:37.127470Z","submitted_at":"2023-02-22T11:49:12Z","title":"Behavior Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11312","snapshot_observed_at":"2026-08-07T12:05:26.085023Z","title":"Behavior proximal policy optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00795","last_updated":"2025-09-11T03:42:40Z","snapshot_observed_at":"2026-08-09T10:56:37.642977Z","submitted_at":"2025-06-01T02:49:26Z","title":"Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization","version":3},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T12:05:26.085023Z"},"links":{"cited_paper":"/paper/2302.11312","citing_paper":"/paper/2506.00795"},"observation_digest":"sha256:2d147d51e4dec3265015894073ec2e694dfb505908317a99f2aef42cbf11d128","observation_id":"2de92e6a-ec70-4159-9a24-cf51af5f8e47","resolution":{"observed_at":"2026-08-07T12:05:26.085023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11312","last_updated":"2023-02-22T11:49:12Z","snapshot_observed_at":"2026-08-04T08:55:37.127470Z","submitted_at":"2023-02-22T11:49:12Z","title":"Behavior Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":"2302.11312","doi":"10.48550/arxiv.2302.11312","metadata_source":"arxiv_reference","pith_arxiv_id":"2302.11312","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Behavior proximal policy optimization","venue":"arXiv (Cornell University)","work_id":"6978277e-38bc-4261-bc49-6762abec3fa5","year":2023},"citing_paper":{"arxiv_id":"2604.02438","last_updated":"2026-05-09T18:59:30Z","snapshot_observed_at":"2026-08-03T15:17:23.743228Z","submitted_at":"2026-04-02T18:09:11Z","title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-13T21:35:52.012244Z"},"links":{"cited_paper":"/paper/2302.11312","citing_paper":"/paper/2604.02438"},"observation_digest":"sha256:aed7056057deacf671c238af8e903cefb30807ee6862ab79150bbe3432681760","observation_id":"ae06fb0f-9b78-4722-af00-df34d5711fd4","resolution":{"observed_at":"2026-05-13T21:38:18.462367Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11312","last_updated":"2023-02-22T11:49:12Z","snapshot_observed_at":"2026-08-04T08:55:37.127470Z","submitted_at":"2023-02-22T11:49:12Z","title":"Behavior Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":"2302.11312","doi":"10.48550/arxiv.2302.11312","metadata_source":"arxiv_reference","pith_arxiv_id":"2302.11312","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Behavior proximal policy optimization","venue":"arXiv (Cornell University)","work_id":"6978277e-38bc-4261-bc49-6762abec3fa5","year":2023},"citing_paper":{"arxiv_id":"2605.18675","last_updated":"2026-05-18T17:15:27Z","snapshot_observed_at":"2026-07-06T23:29:29.105126Z","submitted_at":"2026-05-18T17:15:27Z","title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-20T13:11:16.568415Z"},"links":{"cited_paper":"/paper/2302.11312","citing_paper":"/paper/2605.18675"},"observation_digest":"sha256:e961e1a41fe6d358998000e32d69eab18ed7b817f1205bcdbe62ddb25e41c6fc","observation_id":"b8b72fd1-6758-4061-b1cc-1b21a4a45727","resolution":{"observed_at":"2026-05-20T13:13:18.036585Z","resolver_source":"arxiv_id","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/2302.11312/citation-record","integrity":"/paper/2302.11312/integrity","json":"/paper/2302.11312/citation-record.json","paper":"/paper/2302.11312"},"outbound":[],"paper":{"arxiv_id":"2302.11312","last_updated":"2023-02-22T11:49:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T08:55:37.127470Z","submitted_at":"2023-02-22T11:49:12Z","title":"Behavior Proximal Policy Optimization"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2302.11312."}