{"as_of":"2026-08-11T09:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:89be7c1b4c4dc753f6841dc4088f04808df8882bc80a12cee57be19aa2b49a84","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":"2026-08-11T06:34:44.6726+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":"2026-06-28T15:52:16.912981Z","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":"2026-07-01T21:56:16.606118Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.15141","last_updated":"2022-11-06T01:29:38Z","snapshot_observed_at":"2026-08-11T02:00:13.405447Z","submitted_at":"2022-09-30T00:07:48Z","title":"On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs","version":2},"cited_work":{"arxiv_id":"2209.15141","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2209.15141","snapshot_observed_at":"2026-07-01T21:56:16.606118Z","title":"and Sutton, R","venue":null,"work_id":"c2f6e198-7f61-455d-b100-05e5e6ca04f3","year":null},"citing_paper":{"arxiv_id":"2606.04029","last_updated":"2026-06-06T23:43:36Z","snapshot_observed_at":"2026-08-09T04:19:11.332111Z","submitted_at":"2026-06-01T19:40:10Z","title":"Position: Deployed Reinforcement Learning should be Continual","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T15:52:16.912981Z"},"links":{"cited_paper":"/paper/2209.15141","citing_paper":"/paper/2606.04029"},"observation_digest":"sha256:aaa542783e039da9a930435b8d60f395e1e84136068f98bf5085f23029671d69","observation_id":"57da014b-a1ab-4e2f-860b-dd73df5d1e51","resolution":{"observed_at":"2026-07-01T21:56:16.608428Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2209.15141/citation-record","integrity":"/paper/2209.15141/integrity","json":"/paper/2209.15141/citation-record.json","paper":"/paper/2209.15141"},"outbound":[],"paper":{"arxiv_id":"2209.15141","last_updated":"2022-11-06T01:29:38Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T02:00:13.405447Z","submitted_at":"2022-09-30T00:07:48Z","title":"On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2209.15141."}