{"as_of":"2026-08-08T05:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a44bc22bed3b998767bf6a8c695bf70d84b87bcd27a7aa42f64008fcf3036773","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T04:54:01.740262Z","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":"2026-07-04T05:39:40.730745Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.15332","last_updated":"2023-03-22T22:24:18Z","snapshot_observed_at":"2026-07-06T12:03:10.121189Z","submitted_at":"2021-10-28T17:46:14Z","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.15332","snapshot_observed_at":"2026-08-07T04:54:01.740262Z","title":"and Kallus, N","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09940","last_updated":"2025-06-11T17:06:57Z","snapshot_observed_at":"2026-08-07T04:34:49.017127Z","submitted_at":"2025-06-11T17:06:57Z","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-07T04:54:01.740262Z"},"links":{"cited_paper":"/paper/2110.15332","citing_paper":"/paper/2506.09940"},"observation_digest":"sha256:62bf4395c4122551ab58d056b33c1829582fc00403b15a4aac42629fdd916126","observation_id":"eb476f26-f3a0-424c-852f-3a73651be08b","resolution":{"observed_at":"2026-08-07T04:54:01.740262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.15332","last_updated":"2023-03-22T22:24:18Z","snapshot_observed_at":"2026-07-06T12:03:10.121189Z","submitted_at":"2021-10-28T17:46:14Z","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","version":2},"cited_work":{"arxiv_id":"2110.15332","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.15332","snapshot_observed_at":"2026-07-04T05:39:40.730745Z","title":"arXiv preprint arXiv:2110.15332 , year=","venue":null,"work_id":"00121c39-de54-4f81-b29c-9ecc6bc3b380","year":null},"citing_paper":{"arxiv_id":"2606.20206","last_updated":"2026-06-18T13:19:43Z","snapshot_observed_at":"2026-08-06T08:02:19.305046Z","submitted_at":"2026-06-18T13:19:43Z","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-06-26T15:38:16.806415Z"},"links":{"cited_paper":"/paper/2110.15332","citing_paper":"/paper/2606.20206"},"observation_digest":"sha256:ede326a2efee6bd677870eb39b282409945e827729160a152f982c7f5d2417ca","observation_id":"36241cbd-2163-4959-ab9e-d609849c06db","resolution":{"observed_at":"2026-07-04T05:39:40.732507Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.15332/citation-record","integrity":"/paper/2110.15332/integrity","json":"/paper/2110.15332/citation-record.json","paper":"/paper/2110.15332"},"outbound":[],"paper":{"arxiv_id":"2110.15332","last_updated":"2023-03-22T22:24:18Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T12:03:10.121189Z","submitted_at":"2021-10-28T17:46:14Z","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2110.15332."}