{"as_of":"2026-08-12T22:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5d34dc583ebebcc2bf62ef239c21f746dfbfaa9b8380cc05bdb8eb5b7e41aa57","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T18:35:00.783466Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-15T15:35:10.940163Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.08050","last_updated":"2021-03-14T22:11:40Z","snapshot_observed_at":"2026-08-08T04:27:06.606234Z","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","version":1},"cited_work":{"arxiv_id":"2103.08050","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.08050","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.08050 , year=","venue":null,"work_id":"2d725222-1c52-4333-9f55-4c17481dfb44","year":null},"citing_paper":{"arxiv_id":"2211.15657","last_updated":"2023-07-10T07:25:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-28T18:59:02Z","title":"Is Conditional Generative Modeling all you need for Decision-Making?","version":4},"reference_index":255,"source":"arxiv_source","source_observed_at":"2026-05-15T15:35:10.593969Z"},"links":{"cited_paper":"/paper/2103.08050","citing_paper":"/paper/2211.15657"},"observation_digest":"sha256:e8711454ea2d783a7405e768d292727409a60f5860314673b9044e99e755683a","observation_id":"2efcb5ac-af78-41d8-8814-bfdcb59efcf1","resolution":{"observed_at":"2026-05-15T15:35:10.943347Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.08050","last_updated":"2021-03-14T22:11:40Z","snapshot_observed_at":"2026-08-08T04:27:06.606234Z","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.08050","snapshot_observed_at":"2026-08-11T18:35:00.783466Z","title":"Offline reinforcement learning with fisher divergence critic regularization.arXiv preprint arXiv:2103.08050, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07762","last_updated":"2025-07-02T08:19:18Z","snapshot_observed_at":"2026-08-12T08:03:44.451117Z","submitted_at":"2024-12-10T18:57:12Z","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T18:35:00.783466Z"},"links":{"cited_paper":"/paper/2103.08050","citing_paper":"/paper/2412.07762"},"observation_digest":"sha256:6ff2653a4ad30539993d6c980e0c0217b03916685f8bddf60e4602c31ce7d3f3","observation_id":"b69ac022-c0a2-430f-a3ba-355a92657723","resolution":{"observed_at":"2026-08-11T18:35:00.783466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.08050","last_updated":"2021-03-14T22:11:40Z","snapshot_observed_at":"2026-08-08T04:27:06.606234Z","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.08050","snapshot_observed_at":"2026-08-11T11:24:29.041728Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.15534","last_updated":"2025-02-25T23:42:25Z","snapshot_observed_at":"2026-08-11T11:18:44.274160Z","submitted_at":"2024-12-20T03:48:53Z","title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T11:24:29.041728Z"},"links":{"cited_paper":"/paper/2103.08050","citing_paper":"/paper/2412.15534"},"observation_digest":"sha256:2818cbbaf393120a268ff6312574ba105d6e68fe7dba1d28c0884cc084d0909d","observation_id":"0b14da1d-ef77-4854-8252-b9dfe85f047f","resolution":{"observed_at":"2026-08-11T11:24:29.041728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.08050","last_updated":"2021-03-14T22:11:40Z","snapshot_observed_at":"2026-08-08T04:27:06.606234Z","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.08050","snapshot_observed_at":"2026-08-04T11:01:30.763300Z","title":"Offline reinforcement learning with fisher divergence critic regularization, 2021 b","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.07650","last_updated":"2026-05-30T05:26:12Z","snapshot_observed_at":"2026-08-04T11:01:21.243413Z","submitted_at":"2025-10-09T00:57:40Z","title":"Value Flows","version":4},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T11:01:30.763300Z"},"links":{"cited_paper":"/paper/2103.08050","citing_paper":"/paper/2510.07650"},"observation_digest":"sha256:f91690ccaa54cc22093c580e78e83b7e8b1ababf401a80a3809b59a540680faa","observation_id":"12f3aa42-cfc7-4cde-bf2a-ed324aeeb224","resolution":{"observed_at":"2026-08-04T11:01:30.763300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2103.08050/citation-record","integrity":"/paper/2103.08050/integrity","json":"/paper/2103.08050/citation-record.json","paper":"/paper/2103.08050"},"outbound":[],"paper":{"arxiv_id":"2103.08050","last_updated":"2021-03-14T22:11:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T04:27:06.606234Z","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2103.08050."}