{"as_of":"2026-08-05T16:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ab126f0c3a0ad36957885d6e6feac62aa83b259b33ad25d54c16fff54e5101d","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":"2026-08-05T06:32:48.257954+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":"2026-06-29T09:17:56.858336Z","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":"2026-06-29T09:23:16.496406Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.11745","last_updated":"2024-12-22T03:16:25Z","snapshot_observed_at":"2026-08-04T19:52:32.549798Z","submitted_at":"2022-09-23T17:47:24Z","title":"Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond","version":4},"cited_work":{"arxiv_id":"2209.11745","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2209.11745","snapshot_observed_at":"2026-06-29T09:23:16.496406Z","title":"Yan Dai, Qiwen Cui, and Simon S","venue":null,"work_id":"dcb2ff90-b1cf-4401-8ad7-1efbad6527d9","year":null},"citing_paper":{"arxiv_id":"2605.03125","last_updated":"2026-05-06T22:03:28Z","snapshot_observed_at":"2026-08-04T04:13:10.377270Z","submitted_at":"2026-05-04T20:04:52Z","title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-08T19:13:15.234351Z"},"links":{"cited_paper":"/paper/2209.11745","citing_paper":"/paper/2605.03125"},"observation_digest":"sha256:b681e09c64175e369a99d958e880521742b0dc5e3bb4e263bcb3757c7ff650fb","observation_id":"43508701-9f48-4bdc-8ae4-da6082868c7a","resolution":{"observed_at":"2026-05-09T06:00:35.958127Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.11745","last_updated":"2024-12-22T03:16:25Z","snapshot_observed_at":"2026-08-04T19:52:32.549798Z","submitted_at":"2022-09-23T17:47:24Z","title":"Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond","version":4},"cited_work":{"arxiv_id":"2209.11745","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2209.11745","snapshot_observed_at":"2026-06-29T09:23:16.496406Z","title":"Yan Dai, Qiwen Cui, and Simon S","venue":null,"work_id":"dcb2ff90-b1cf-4401-8ad7-1efbad6527d9","year":null},"citing_paper":{"arxiv_id":"2605.29645","last_updated":"2026-05-28T09:12:20Z","snapshot_observed_at":"2026-07-06T23:39:01.234601Z","submitted_at":"2026-05-28T09:12:20Z","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T09:17:56.858336Z"},"links":{"cited_paper":"/paper/2209.11745","citing_paper":"/paper/2605.29645"},"observation_digest":"sha256:0f7a13c39fa71222cf613fffd8c1052f57bb01d10f451ad9f3586a862f1d7fb2","observation_id":"6588cd9b-2562-4761-ad51-59e602d11e84","resolution":{"observed_at":"2026-06-29T09:23:16.498057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2209.11745/citation-record","integrity":"/paper/2209.11745/integrity","json":"/paper/2209.11745/citation-record.json","paper":"/paper/2209.11745"},"outbound":[],"paper":{"arxiv_id":"2209.11745","last_updated":"2024-12-22T03:16:25Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T19:52:32.549798Z","submitted_at":"2022-09-23T17:47:24Z","title":"Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2209.11745."}