{"as_of":"2026-08-13T22:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:db8b7968a7c9ebf592413e912b94ec4dbcae5a03de1f8daed863caffdfe4a826","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":"2026-08-13T06:32:02.005865+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":"2026-08-11T19:24:39.272202Z","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":"2026-05-12T05:41:23.524551Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.05991","last_updated":"2023-06-09T15:59:39Z","snapshot_observed_at":"2026-08-13T11:20:13.089197Z","submitted_at":"2023-06-09T15:59:39Z","title":"Approximate information state based convergence analysis of recurrent Q-learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05991","snapshot_observed_at":"2026-08-11T19:24:39.272202Z","title":"Seyedsalehi, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06735","last_updated":"2024-12-31T00:22:52Z","snapshot_observed_at":"2026-08-12T08:44:26.307113Z","submitted_at":"2024-12-09T18:26:04Z","title":"Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T19:24:39.272202Z"},"links":{"cited_paper":"/paper/2306.05991","citing_paper":"/paper/2412.06735"},"observation_digest":"sha256:4163a9dfcdc670650bd286f6e1956e03452875426e098a63ead52e8646729f51","observation_id":"11dea12b-954f-49e2-92a9-b37acfda843d","resolution":{"observed_at":"2026-08-11T19:24:39.272202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05991","last_updated":"2023-06-09T15:59:39Z","snapshot_observed_at":"2026-08-13T11:20:13.089197Z","submitted_at":"2023-06-09T15:59:39Z","title":"Approximate information state based convergence analysis of recurrent Q-learning","version":1},"cited_work":{"arxiv_id":"2306.05991","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.05991","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2306.05991 , year=","venue":null,"work_id":"36e24464-7385-4921-8919-58b3eed68d13","year":null},"citing_paper":{"arxiv_id":"2605.10816","last_updated":"2026-05-11T16:34:28Z","snapshot_observed_at":"2026-08-11T08:26:40.097645Z","submitted_at":"2026-05-11T16:34:28Z","title":"Policy Gradient Methods for Non-Markovian Reinforcement Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-12T05:36:54.894355Z"},"links":{"cited_paper":"/paper/2306.05991","citing_paper":"/paper/2605.10816"},"observation_digest":"sha256:a094d9c4f0f852eb4e6dcc59b7f43096f78e6f37104a3a72925f4fb1bb8d9954","observation_id":"9bbdbc8e-9d32-4e90-8ddd-399136549782","resolution":{"observed_at":"2026-05-12T05:41:23.528303Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2306.05991/citation-record","integrity":"/paper/2306.05991/integrity","json":"/paper/2306.05991/citation-record.json","paper":"/paper/2306.05991"},"outbound":[],"paper":{"arxiv_id":"2306.05991","last_updated":"2023-06-09T15:59:39Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T11:20:13.089197Z","submitted_at":"2023-06-09T15:59:39Z","title":"Approximate information state based convergence analysis of recurrent Q-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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.05991."}