{"as_of":"2026-08-08T20:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a987d778c5e39f76e2e694e5696425e5178940220a7e25087d62e0c696f48adb","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:10:38.975486Z","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":"2026-05-16T19:58:23.640103Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.09681","last_updated":"2024-06-04T21:19:10Z","snapshot_observed_at":"2026-08-07T20:18:58.674105Z","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09681","snapshot_observed_at":"2026-08-07T14:10:38.975486Z","title":"Harnessing density ratios for online reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","snapshot_observed_at":"2026-08-08T15:11:42.219804Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T14:10:38.975486Z"},"links":{"cited_paper":"/paper/2401.09681","citing_paper":"/paper/2505.20268"},"observation_digest":"sha256:6a293ee3bc252dabd255b97f57260be3ff3b00d0867292560d25a15fa0d3275f","observation_id":"2edd07fa-d3a2-4665-a39d-9a1c8bcf4e92","resolution":{"observed_at":"2026-08-07T14:10:38.975486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09681","last_updated":"2024-06-04T21:19:10Z","snapshot_observed_at":"2026-08-07T20:18:58.674105Z","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09681","snapshot_observed_at":"2026-08-07T13:44:54.889918Z","title":"J., Jiang, N., Sekhari, A., and Xie, T","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21395","last_updated":"2025-05-27T16:23:24Z","snapshot_observed_at":"2026-08-07T13:26:21.678395Z","submitted_at":"2025-05-27T16:23:24Z","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T13:44:54.889918Z"},"links":{"cited_paper":"/paper/2401.09681","citing_paper":"/paper/2505.21395"},"observation_digest":"sha256:1028feb41e5a84ef25508ce06dec85ee4084ad50e55557980636b6ed59fcda05","observation_id":"f2fea3a5-9512-4a06-9378-3726f05d2273","resolution":{"observed_at":"2026-08-07T13:44:54.889918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09681","last_updated":"2024-06-04T21:19:10Z","snapshot_observed_at":"2026-08-07T20:18:58.674105Z","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2401.09681","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.09681","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"J., Jiang, N., Sekhari, A., and Xie, T","venue":null,"work_id":"7e924ca5-b65a-49fe-b72c-ae433fcdb4fd","year":null},"citing_paper":{"arxiv_id":"2512.23805","last_updated":"2026-05-07T18:46:25Z","snapshot_observed_at":"2026-07-06T22:40:17.725041Z","submitted_at":"2025-12-29T19:04:40Z","title":"Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T19:05:34.417424Z"},"links":{"cited_paper":"/paper/2401.09681","citing_paper":"/paper/2512.23805"},"observation_digest":"sha256:1955d81e2d6c813efcdca9b992db7896fb6b05507900d104c4e847c99d059cda","observation_id":"76f27b68-0440-4127-ae9f-71424310b2c5","resolution":{"observed_at":"2026-05-16T19:08:19.141856Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09681","last_updated":"2024-06-04T21:19:10Z","snapshot_observed_at":"2026-08-07T20:18:58.674105Z","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2401.09681","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.09681","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"J., Jiang, N., Sekhari, A., and Xie, T","venue":null,"work_id":"7e924ca5-b65a-49fe-b72c-ae433fcdb4fd","year":null},"citing_paper":{"arxiv_id":"2512.23927","last_updated":"2026-05-07T21:18:45Z","snapshot_observed_at":"2026-08-06T14:29:24.244747Z","submitted_at":"2025-12-30T00:58:35Z","title":"Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T19:53:23.616808Z"},"links":{"cited_paper":"/paper/2401.09681","citing_paper":"/paper/2512.23927"},"observation_digest":"sha256:664f4c7ecc08ea87d3768cad882dc7faaef328c2d473fcbdb36e82a7ba20f736","observation_id":"ae5b0cf0-4976-45d9-abec-cbd480dd938d","resolution":{"observed_at":"2026-05-16T19:58:23.641976Z","resolver_source":"arxiv_id","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/2401.09681/citation-record","integrity":"/paper/2401.09681/integrity","json":"/paper/2401.09681/citation-record.json","paper":"/paper/2401.09681"},"outbound":[],"paper":{"arxiv_id":"2401.09681","last_updated":"2024-06-04T21:19:10Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T20:18:58.674105Z","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online 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 4 inbound Pith citation observations for arXiv:2401.09681."}