{"as_of":"2026-08-22T03:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8471d0a0e084d80716c99f84e4cccda8b9217f13622b4c5d2acafbff776cb622","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:26:49.237033Z","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":"2026-08-07T04:54:08.291306Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.09907","last_updated":"2024-10-14T22:26:38Z","snapshot_observed_at":"2026-08-20T05:04:14.683353Z","submitted_at":"2021-02-19T13:01:40Z","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.09907","snapshot_observed_at":"2026-08-11T20:26:49.237033Z","title":"Instrumental variable value iteration for causal offline reinforcement learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05783","last_updated":"2024-12-08T02:28:58Z","snapshot_observed_at":"2026-08-20T05:01:00.549513Z","submitted_at":"2024-12-08T02:28:58Z","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-11T20:26:49.237033Z"},"links":{"cited_paper":"/paper/2102.09907","citing_paper":"/paper/2412.05783"},"observation_digest":"sha256:ac1b2b683a7eca8c986680f988df9bfb02f9f365e606ec5d224f6047793e44e3","observation_id":"ff919683-2e4f-47ab-94b7-05a99ee2375c","resolution":{"observed_at":"2026-08-11T20:26:49.237033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.09907","last_updated":"2024-10-14T22:26:38Z","snapshot_observed_at":"2026-08-20T05:04:14.683353Z","submitted_at":"2021-02-19T13:01:40Z","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.09907","snapshot_observed_at":"2026-08-10T21:29:12.048955Z","title":"Instrumental variable value iteration for causal offline reinforcement learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04898","last_updated":"2025-01-09T01:22:22Z","snapshot_observed_at":"2026-08-19T21:21:20.232287Z","submitted_at":"2025-01-09T01:22:22Z","title":"Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T21:29:12.048955Z"},"links":{"cited_paper":"/paper/2102.09907","citing_paper":"/paper/2501.04898"},"observation_digest":"sha256:8f4e54391ce58bd60b04af93c090b60504eccd938ca55a38fd4a3dcc84741e6e","observation_id":"bd6cdb46-322a-42c6-a167-5e1943d2eb2a","resolution":{"observed_at":"2026-08-10T21:29:12.048955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.09907","last_updated":"2024-10-14T22:26:38Z","snapshot_observed_at":"2026-08-20T05:04:14.683353Z","submitted_at":"2021-02-19T13:01:40Z","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2102.09907","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.09907","snapshot_observed_at":"2026-08-07T04:54:08.291306Z","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","venue":"stat.ML","work_id":"337fc120-d563-46a0-aa68-e36c657b52ee","year":2021},"citing_paper":{"arxiv_id":"2506.09940","last_updated":"2025-06-11T17:06:57Z","snapshot_observed_at":"2026-08-15T02:45:08.342678Z","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":2023,"source":"pdf_text","source_observed_at":"2026-08-07T04:54:03.658128Z"},"links":{"cited_paper":"/paper/2102.09907","citing_paper":"/paper/2506.09940"},"observation_digest":"sha256:94adbc57ee113e2b375e50816e108a76f20de4e5217f1f1ab3e2d025f067a8e7","observation_id":"8fd8f01b-760c-4162-b371-c47fa63a0f77","resolution":{"observed_at":"2026-08-07T04:54:08.476679Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2102.09907/citation-record","integrity":"/paper/2102.09907/integrity","json":"/paper/2102.09907/citation-record.json","paper":"/paper/2102.09907"},"outbound":[],"paper":{"arxiv_id":"2102.09907","last_updated":"2024-10-14T22:26:38Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-20T05:04:14.683353Z","submitted_at":"2021-02-19T13:01:40Z","title":"Instrumental Variable Value Iteration for Causal Offline 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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2102.09907."}