{"as_of":"2026-08-07T20:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23615f6ce27b1ed6d61263e8eae9577db40d6d36e382c7c352025ee9ac6d5941","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":"2026-08-07T06:34:17.273281+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":"2026-07-12T13:42:27.758405Z","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":"2026-05-20T22:09:07.586296Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.12222","last_updated":"2025-03-15T18:12:16Z","snapshot_observed_at":"2026-08-07T17:01:38.670989Z","submitted_at":"2025-03-15T18:12:16Z","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2503.12222","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.12222","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2503.12222 , year=","venue":null,"work_id":"ab41c27d-d62a-4a86-9e17-0f5cf7c0b0c3","year":null},"citing_paper":{"arxiv_id":"2605.09183","last_updated":"2026-05-16T18:02:16Z","snapshot_observed_at":"2026-07-06T23:21:21.560069Z","submitted_at":"2026-05-09T21:48:04Z","title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-05-12T03:27:41.845716Z"},"links":{"cited_paper":"/paper/2503.12222","citing_paper":"/paper/2605.09183"},"observation_digest":"sha256:c6c2db8d2d9e637b4be4ed114c5c366dd7e2f0694c984e0b46501bcff13df782","observation_id":"129b4cae-a94b-424b-8e0e-088aa86661f2","resolution":{"observed_at":"2026-05-12T07:21:25.418014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12222","last_updated":"2025-03-15T18:12:16Z","snapshot_observed_at":"2026-08-07T17:01:38.670989Z","submitted_at":"2025-03-15T18:12:16Z","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2503.12222","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.12222","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2503.12222 , year=","venue":null,"work_id":"ab41c27d-d62a-4a86-9e17-0f5cf7c0b0c3","year":null},"citing_paper":{"arxiv_id":"2605.09183","last_updated":"2026-05-16T18:02:16Z","snapshot_observed_at":"2026-07-06T23:21:21.560069Z","submitted_at":"2026-05-09T21:48:04Z","title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","version":2},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-05-20T22:04:57.245024Z"},"links":{"cited_paper":"/paper/2503.12222","citing_paper":"/paper/2605.09183"},"observation_digest":"sha256:ef2fb14d00d52920df90abdcbf6bf4fcda15504318fe04dc08a5e142b88c3cdd","observation_id":"b7d50eaa-77ff-4278-a3a3-eec278977e64","resolution":{"observed_at":"2026-05-20T22:09:07.590010Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12222","last_updated":"2025-03-15T18:12:16Z","snapshot_observed_at":"2026-08-07T17:01:38.670989Z","submitted_at":"2025-03-15T18:12:16Z","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.12222","snapshot_observed_at":"2026-07-12T13:42:27.758405Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.16933","last_updated":"2026-07-06T13:15:11Z","snapshot_observed_at":"2026-08-06T16:01:13.657296Z","submitted_at":"2026-06-15T16:32:40Z","title":"A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-12T13:42:27.758405Z"},"links":{"cited_paper":"/paper/2503.12222","citing_paper":"/paper/2606.16933"},"observation_digest":"sha256:ae8545dbf91b74ccfb32a32a0122b32f4d61619e585777b0d9485b050b5877ef","observation_id":"22cd3434-3523-4126-ba71-39be66bfede9","resolution":{"observed_at":"2026-07-12T13:42:27.758405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.12222/citation-record","integrity":"/paper/2503.12222/integrity","json":"/paper/2503.12222/citation-record.json","paper":"/paper/2503.12222"},"outbound":[],"paper":{"arxiv_id":"2503.12222","last_updated":"2025-03-15T18:12:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T17:01:38.670989Z","submitted_at":"2025-03-15T18:12:16Z","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.12222."}