{"as_of":"2026-08-08T15:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3133af345c37f233b2ad75a80f2f3706936ecdd961a477898d90f19d02baf861","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:28:41.567710Z","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":"2026-08-07T13:17:03.403559Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.02581","last_updated":"2025-03-01T12:55:13Z","snapshot_observed_at":"2026-08-06T07:06:33.911763Z","submitted_at":"2023-10-04T04:57:35Z","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02581","snapshot_observed_at":"2026-08-07T14:28:41.567710Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.19002","last_updated":"2025-05-25T06:47:36Z","snapshot_observed_at":"2026-08-07T14:19:44.954656Z","submitted_at":"2025-05-25T06:47:36Z","title":"Semi-pessimistic Reinforcement Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:28:41.567710Z"},"links":{"cited_paper":"/paper/2310.02581","citing_paper":"/paper/2505.19002"},"observation_digest":"sha256:c28cebbe6553278600fb8da4a634de3eea9c190e0ab85416d9fb5648aeb6e16d","observation_id":"25183d71-fd7f-4130-8817-1822819b9378","resolution":{"observed_at":"2026-08-07T14:28:41.567710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02581","last_updated":"2025-03-01T12:55:13Z","snapshot_observed_at":"2026-08-06T07:06:33.911763Z","submitted_at":"2023-10-04T04:57:35Z","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2310.02581","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.02581","snapshot_observed_at":"2026-08-07T13:17:03.403559Z","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","venue":"stat.ML","work_id":"a04a3c1f-d31d-41b6-8641-d6d4459db941","year":2023},"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":42,"source":"arxiv_source","source_observed_at":"2026-08-07T13:16:56.834090Z"},"links":{"cited_paper":"/paper/2310.02581","citing_paper":"/paper/2505.22492"},"observation_digest":"sha256:0d73b1dd0d017a28ceb400fa7692d0a894d6ea887d414e2ecee1b63da81fa676","observation_id":"b6029ff5-5b9f-48b3-9947-4d1d444ba384","resolution":{"observed_at":"2026-08-07T13:17:03.551774Z","resolver_source":"local_arxiv","status":"verified_exact"},"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/2310.02581/citation-record","integrity":"/paper/2310.02581/integrity","json":"/paper/2310.02581/citation-record.json","paper":"/paper/2310.02581"},"outbound":[],"paper":{"arxiv_id":"2310.02581","last_updated":"2025-03-01T12:55:13Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-06T07:06:33.911763Z","submitted_at":"2023-10-04T04:57:35Z","title":"Online Estimation and Inference for Robust Policy Evaluation in 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 2 inbound Pith citation observations for arXiv:2310.02581."}