{"as_of":"2026-08-24T01:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a479fd480751b46727b2ef13a4240ae74afffdeac5e0d2acc5347ad59a4656e3","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":"2026-08-23T06:30:58.430688+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":"2026-08-10T16:18:17.386389Z","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":"2026-08-06T16:15:16.199680Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1901.09311","last_updated":"2019-09-27T02:09:54Z","snapshot_observed_at":"2026-08-14T17:25:25.872797Z","submitted_at":"2019-01-27T03:44:42Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.09311","snapshot_observed_at":"2026-08-10T16:18:17.386389Z","title":"Q -learning with UCB exploration is sample efficient for infinite-horizon MDP","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2501.13394","last_updated":"2025-06-15T19:49:41Z","snapshot_observed_at":"2026-08-17T19:24:57.964386Z","submitted_at":"2025-01-23T05:37:33Z","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T16:18:17.386389Z"},"links":{"cited_paper":"/paper/1901.09311","citing_paper":"/paper/2501.13394"},"observation_digest":"sha256:c1c66ad48a7b0b06d7bbcab92df739c1767a2e619edbee17e3943fb79f1005ab","observation_id":"e73cbf13-dca9-4c8c-b6d9-743b092cd34e","resolution":{"observed_at":"2026-08-10T16:18:17.386389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.09311","last_updated":"2019-09-27T02:09:54Z","snapshot_observed_at":"2026-08-14T17:25:25.872797Z","submitted_at":"2019-01-27T03:44:42Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","version":2},"cited_work":{"arxiv_id":"1901.09311","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.09311","snapshot_observed_at":"2026-08-06T16:15:16.199680Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","venue":"cs.LG","work_id":"54822cea-2269-49e2-b852-713076c8b770","year":2019},"citing_paper":{"arxiv_id":"2507.14444","last_updated":"2025-07-19T02:42:41Z","snapshot_observed_at":"2026-08-14T15:14:45.544908Z","submitted_at":"2025-07-19T02:42:41Z","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T16:15:15.669216Z"},"links":{"cited_paper":"/paper/1901.09311","citing_paper":"/paper/2507.14444"},"observation_digest":"sha256:9e3fa9e956cc346f593ec317accc11d0ff391664cf41d3d01e0bb874b4fba4e2","observation_id":"adca8aff-9532-4ec8-85aa-12f2d1a0e8a3","resolution":{"observed_at":"2026-08-06T16:15:16.203077Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.09311","last_updated":"2019-09-27T02:09:54Z","snapshot_observed_at":"2026-08-14T17:25:25.872797Z","submitted_at":"2019-01-27T03:44:42Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.09311","snapshot_observed_at":"2026-08-01T11:40:23.836348Z","title":"Q-learning with ucb exploration is sample efficient for infinite-horizon mdp.arXiv preprint arXiv:1901.09311, 2019","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2607.19854","last_updated":"2026-07-22T07:42:19Z","snapshot_observed_at":"2026-08-13T18:02:52.709964Z","submitted_at":"2026-07-22T07:42:19Z","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T11:40:23.836348Z"},"links":{"cited_paper":"/paper/1901.09311","citing_paper":"/paper/2607.19854"},"observation_digest":"sha256:096c12e22e86a95a2847e7babced4a2fcc8e2dd2be35d87c5c6c0f1678eebc1e","observation_id":"4c7bf4ac-ee8b-40aa-8ac7-de0c812c5dc2","resolution":{"observed_at":"2026-08-01T11:40:23.836348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1901.09311/citation-record","integrity":"/paper/1901.09311/integrity","json":"/paper/1901.09311/citation-record.json","paper":"/paper/1901.09311"},"outbound":[],"paper":{"arxiv_id":"1901.09311","last_updated":"2019-09-27T02:09:54Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T17:25:25.872797Z","submitted_at":"2019-01-27T03:44:42Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1901.09311."}