{"as_of":"2026-08-22T20:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9a8c4d9934b81958c40375964d51b4a6576391a9e7959626bad1ef05b449223f","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":"2026-08-22T06:32:14.747728+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":"2026-05-24T00:35:41.483393Z","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":"2026-05-24T00:35:55.763515Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.11168","last_updated":"2024-07-02T06:57:21Z","snapshot_observed_at":"2026-08-19T14:55:03.464224Z","submitted_at":"2022-05-23T10:15:00Z","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","version":4},"cited_work":{"arxiv_id":"2205.11168","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.11168","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2f7a3878-817c-442d-ac75-d01c29de48c8","year":null},"citing_paper":{"arxiv_id":"2406.05358","last_updated":"2026-04-12T00:40:35Z","snapshot_observed_at":"2026-08-18T16:16:06.524949Z","submitted_at":"2024-06-08T05:27:01Z","title":"Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-24T00:35:41.483393Z"},"links":{"cited_paper":"/paper/2205.11168","citing_paper":"/paper/2406.05358"},"observation_digest":"sha256:5b9d3bae1148d5e19af1839429f5e585c84a573c8ac39a607cecb4c603dd65ab","observation_id":"d7472ae3-6a2a-42bb-b48b-53f79eb087c7","resolution":{"observed_at":"2026-05-24T00:35:55.767241Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.11168/citation-record","integrity":"/paper/2205.11168/integrity","json":"/paper/2205.11168/citation-record.json","paper":"/paper/2205.11168"},"outbound":[],"paper":{"arxiv_id":"2205.11168","last_updated":"2024-07-02T06:57:21Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T14:55:03.464224Z","submitted_at":"2022-05-23T10:15:00Z","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2205.11168."}