{"as_of":"2026-08-18T15:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0dac1ddb6d3e4047acbd50e5a8779b28ab0d203a016d44194c5bf85d414bcd12","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":"2026-08-18T06:34:40.430872+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":"2026-08-15T20:45:55.405318Z","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":"2026-07-04T19:10:05.228039Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.06548","last_updated":"2023-03-17T19:02:46Z","snapshot_observed_at":"2026-08-16T18:45:58.503053Z","submitted_at":"2021-02-12T14:22:05Z","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.06548","snapshot_observed_at":"2026-08-15T20:45:55.405318Z","title":"Is Q-learning minimax optimal? a tight sample complexity analysis.arXiv preprint arXiv:2102.06548, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12462","last_updated":"2026-06-21T21:20:26Z","snapshot_observed_at":"2026-08-17T19:23:25.884434Z","submitted_at":"2025-05-18T15:34:45Z","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:55.405318Z"},"links":{"cited_paper":"/paper/2102.06548","citing_paper":"/paper/2505.12462"},"observation_digest":"sha256:10f232cee26164435a81db3ed14f3fa606927b0b1be1e8823e35bc1d5cbf8ca1","observation_id":"f8309385-1e25-41c3-b22f-454f64601c69","resolution":{"observed_at":"2026-08-15T20:45:55.405318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06548","last_updated":"2023-03-17T19:02:46Z","snapshot_observed_at":"2026-08-16T18:45:58.503053Z","submitted_at":"2021-02-12T14:22:05Z","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.06548","snapshot_observed_at":"2026-08-07T13:32:56.972939Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21796","last_updated":"2025-05-27T21:58:35Z","snapshot_observed_at":"2026-08-15T04:04:03.493304Z","submitted_at":"2025-05-27T21:58:35Z","title":"A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:32:56.972939Z"},"links":{"cited_paper":"/paper/2102.06548","citing_paper":"/paper/2505.21796"},"observation_digest":"sha256:3c7263f2f9ba60c3165fbbfa46cf29df1b7c53ab197e2579f4e8234092eb2130","observation_id":"23803ec9-8bf0-42d5-93ea-e8cd0227ca00","resolution":{"observed_at":"2026-08-07T13:32:56.972939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06548","last_updated":"2023-03-17T19:02:46Z","snapshot_observed_at":"2026-08-16T18:45:58.503053Z","submitted_at":"2021-02-12T14:22:05Z","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","version":4},"cited_work":{"arxiv_id":"2102.06548","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.06548","snapshot_observed_at":"2026-07-04T19:10:05.228039Z","title":"Chenbei Lu, Zaiwei Chen, Tongxin Li, Chenye Wu, and Adam Wierman","venue":null,"work_id":"febbcd0a-6d6a-4d3e-83b2-293e949ff1a8","year":null},"citing_paper":{"arxiv_id":"2606.25170","last_updated":"2026-06-23T21:02:18Z","snapshot_observed_at":"2026-08-08T11:53:10.462502Z","submitted_at":"2026-06-23T21:02:18Z","title":"Minimax PAC Bounds for Learning in Exogenous Contextual MDPs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-25T21:39:39.968655Z"},"links":{"cited_paper":"/paper/2102.06548","citing_paper":"/paper/2606.25170"},"observation_digest":"sha256:d46db50c88f0a75b8f730ffb6eb4740294d82491ada5b719f90f5b80dc4bbf2f","observation_id":"5cd57cd6-b470-4294-86a0-cbfe1e8326b1","resolution":{"observed_at":"2026-07-04T19:10:05.229713Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2102.06548/citation-record","integrity":"/paper/2102.06548/integrity","json":"/paper/2102.06548/citation-record.json","paper":"/paper/2102.06548"},"outbound":[],"paper":{"arxiv_id":"2102.06548","last_updated":"2023-03-17T19:02:46Z","latest_version":4,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-16T18:45:58.503053Z","submitted_at":"2021-02-12T14:22:05Z","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2102.06548."}