{"as_of":"2026-08-17T18:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7942f7ef8daf3236ce6aee81975acd9f2d87de1659738f1f584c5b940c3446e8","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":"2026-08-17T06:30:58.91139+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":"2026-08-14T10:27:42.014837Z","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":"2026-08-11T20:26:50.063789Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1905.00360","last_updated":"2019-05-01T16:19:28Z","snapshot_observed_at":"2026-08-14T16:38:43.656509Z","submitted_at":"2019-05-01T16:19:28Z","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00360","snapshot_observed_at":"2026-08-14T10:27:42.014837Z","title":"and Jiang, N","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1909.01150","last_updated":"2019-11-12T21:42:43Z","snapshot_observed_at":"2026-08-15T10:56:00.207708Z","submitted_at":"2019-08-29T15:38:19Z","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-14T10:27:42.014837Z"},"links":{"cited_paper":"/paper/1905.00360","citing_paper":"/paper/1909.01150"},"observation_digest":"sha256:d77dab90ab2e73b3272fe2c6c965d2c203d43db5bd4f7de6be00c1e5c178bf9b","observation_id":"7904e087-0c57-46d9-9044-4c3d3161e69e","resolution":{"observed_at":"2026-08-14T10:27:42.014837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00360","last_updated":"2019-05-01T16:19:28Z","snapshot_observed_at":"2026-08-14T16:38:43.656509Z","submitted_at":"2019-05-01T16:19:28Z","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1905.00360","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.00360","snapshot_observed_at":"2026-08-11T20:26:50.063789Z","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","venue":"cs.LG","work_id":"b0b5b3b7-40a2-4fdc-a67d-e9185adfc446","year":2019},"citing_paper":{"arxiv_id":"2412.05783","last_updated":"2024-12-08T02:28:58Z","snapshot_observed_at":"2026-08-16T23:31:06.738366Z","submitted_at":"2024-12-08T02:28:58Z","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T20:26:49.073582Z"},"links":{"cited_paper":"/paper/1905.00360","citing_paper":"/paper/2412.05783"},"observation_digest":"sha256:b22d7c1640d4e36fc6de4398e7368dfa9dc642253119653e2f662b131340d441","observation_id":"61ddd041-b55b-4d1e-932d-44105215db94","resolution":{"observed_at":"2026-08-11T20:26:50.069475Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1905.00360/citation-record","integrity":"/paper/1905.00360/integrity","json":"/paper/1905.00360/citation-record.json","paper":"/paper/1905.00360"},"outbound":[],"paper":{"arxiv_id":"1905.00360","last_updated":"2019-05-01T16:19:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T16:38:43.656509Z","submitted_at":"2019-05-01T16:19:28Z","title":"Information-Theoretic Considerations in Batch 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1905.00360."}