{"as_of":"2026-08-08T13:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aac80209d82740908f476630fb98b0b313781b3c2d1974e62d1a0751fb6bbf31","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T13:16:56.740396Z","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":"2026-08-07T13:17:03.755725Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.02226","last_updated":"2025-03-20T05:00:23Z","snapshot_observed_at":"2026-07-06T19:26:49.672415Z","submitted_at":"2024-10-03T05:47:55Z","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2410.02226","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.02226","snapshot_observed_at":"2026-08-07T13:17:03.755725Z","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","venue":"cs.LG","work_id":"8b833e22-96d0-4b69-9736-04a3f042d22a","year":2024},"citing_paper":{"arxiv_id":"2505.22492","last_updated":"2025-05-28T15:42:20Z","snapshot_observed_at":"2026-08-08T07:58:26.228808Z","submitted_at":"2025-05-28T15:42:20Z","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T13:16:56.740396Z"},"links":{"cited_paper":"/paper/2410.02226","citing_paper":"/paper/2505.22492"},"observation_digest":"sha256:02d29b5725a0ae67eb988b772eb7bdebbd1aa453cdbed65216f793f789586c06","observation_id":"20212785-c506-4558-a002-57494379b523","resolution":{"observed_at":"2026-08-07T13:17:03.912586Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.02226/citation-record","integrity":"/paper/2410.02226/integrity","json":"/paper/2410.02226/citation-record.json","paper":"/paper/2410.02226"},"outbound":[],"paper":{"arxiv_id":"2410.02226","last_updated":"2025-03-20T05:00:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:26:49.672415Z","submitted_at":"2024-10-03T05:47:55Z","title":"Doubly Optimal Policy Evaluation for Reinforcement 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2410.02226."}