{"as_of":"2026-08-09T07:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f8366799b96513ba3cf3b351b5776d6f0fb7cba1c0dc8a8f82cb185ac6c8755","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:41:52.449262Z","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":"2026-08-07T14:41:53.401042Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1004.5229","last_updated":"2010-10-13T10:11:39Z","snapshot_observed_at":"2026-08-09T05:30:34.833731Z","submitted_at":"2010-04-29T09:31:55Z","title":"Optimism in Reinforcement Learning and Kullback-Leibler Divergence","version":3},"cited_work":{"arxiv_id":"1004.5229","doi":null,"metadata_source":"pith","pith_arxiv_id":"1004.5229","snapshot_observed_at":"2026-08-07T14:41:53.401042Z","title":"Optimism in Reinforcement Learning and Kullback-Leibler Divergence","venue":"cs.LG","work_id":"2a682b3c-01e1-4c3f-927f-d027601d1725","year":2010},"citing_paper":{"arxiv_id":"2505.18064","last_updated":"2025-05-23T16:11:39Z","snapshot_observed_at":"2026-08-07T14:33:59.436108Z","submitted_at":"2025-05-23T16:11:39Z","title":"Asymptotically optimal regret in communicating Markov decision processes","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-07T14:41:52.449262Z"},"links":{"cited_paper":"/paper/1004.5229","citing_paper":"/paper/2505.18064"},"observation_digest":"sha256:78271de5349f642ad8b19406cff4d30b40c75c50b8eb63f6dd90e16fc6a262fe","observation_id":"aa5e2e6b-1d62-480e-ada3-dfe14b0cbdb4","resolution":{"observed_at":"2026-08-07T14:41:53.465716Z","resolver_source":"local_arxiv","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/1004.5229/citation-record","integrity":"/paper/1004.5229/integrity","json":"/paper/1004.5229/citation-record.json","paper":"/paper/1004.5229"},"outbound":[],"paper":{"arxiv_id":"1004.5229","last_updated":"2010-10-13T10:11:39Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T05:30:34.833731Z","submitted_at":"2010-04-29T09:31:55Z","title":"Optimism in Reinforcement Learning and Kullback-Leibler Divergence"},"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 1 inbound Pith citation observation for arXiv:1004.5229."}