{"as_of":"2026-08-10T00:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:918af4d13a84ad755c9a38f4da10ea5088b93e512dcb695bd994ba7b57b45392","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":"2026-08-01T11:40:26.138252Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1803.01626","last_updated":"2018-03-05T12:23:42Z","snapshot_observed_at":"2026-07-06T06:26:37.380259Z","submitted_at":"2018-03-05T12:23:42Z","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01626","snapshot_observed_at":"2026-08-01T11:40:26.138252Z","title":"Variance-aware regret bounds for undis- counted reinforcement learning in mdps.arXiv preprint arXiv:1803.01626, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.19854","last_updated":"2026-07-22T07:42:19Z","snapshot_observed_at":"2026-08-01T11:40:18.790734Z","submitted_at":"2026-07-22T07:42:19Z","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T11:40:26.138252Z"},"links":{"cited_paper":"/paper/1803.01626","citing_paper":"/paper/2607.19854"},"observation_digest":"sha256:f5c0295702ce9fed3083012fb51ec2392fd53b844c1bb55a645bfe0dee0014e2","observation_id":"d18ebd5e-b905-4ede-a069-f6526fb93e1a","resolution":{"observed_at":"2026-08-01T11:40:26.138252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1803.01626/citation-record","integrity":"/paper/1803.01626/integrity","json":"/paper/1803.01626/citation-record.json","paper":"/paper/1803.01626"},"outbound":[],"paper":{"arxiv_id":"1803.01626","last_updated":"2018-03-05T12:23:42Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-07-06T06:26:37.380259Z","submitted_at":"2018-03-05T12:23:42Z","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1803.01626."}