{"as_of":"2026-08-15T12:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:36bd3be8550b864389a969e94f33514a228af0f7cf6fe39ace397f076c34ea5e","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":"2026-08-15T06:32:42.880941+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":"2026-08-14T04:54:13.784020Z","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":"2026-08-14T04:54:13.999483Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1901.00210","last_updated":"2019-11-01T20:35:28Z","snapshot_observed_at":"2026-08-14T17:36:09.834261Z","submitted_at":"2019-01-01T21:17:21Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","version":4},"cited_work":{"arxiv_id":"1901.00210","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.00210","snapshot_observed_at":"2026-08-14T04:54:13.999483Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","venue":"cs.LG","work_id":"9d24c8a0-8562-415a-b027-103df0a9fa52","year":2019},"citing_paper":{"arxiv_id":"1909.02506","last_updated":"2020-06-20T17:17:19Z","snapshot_observed_at":"2026-08-14T04:45:55.535698Z","submitted_at":"2019-09-05T16:20:41Z","title":"$\\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:54:13.784020Z"},"links":{"cited_paper":"/paper/1901.00210","citing_paper":"/paper/1909.02506"},"observation_digest":"sha256:72f4bb582554a4770eff5ab61245dd055bcadac5ae3411cb6f502b288bc61f06","observation_id":"7541a362-e33a-4c63-b5bc-e4617e947fd7","resolution":{"observed_at":"2026-08-14T04:54:14.003851Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.00210","last_updated":"2019-11-01T20:35:28Z","snapshot_observed_at":"2026-08-14T17:36:09.834261Z","submitted_at":"2019-01-01T21:17:21Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.00210","snapshot_observed_at":"2026-08-02T20:42:07.973187Z","title":null,"venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2602.22810","last_updated":"2026-06-23T02:26:25Z","snapshot_observed_at":"2026-08-06T15:15:16.654587Z","submitted_at":"2026-02-26T09:50:15Z","title":"Multi-agent imitation learning with function approximation: Linear Markov games and beyond","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T20:42:07.973187Z"},"links":{"cited_paper":"/paper/1901.00210","citing_paper":"/paper/2602.22810"},"observation_digest":"sha256:9f38c32fad96a5431e0c260716f388801e514296d5ab4fc1166bd65a489c1368","observation_id":"917d3c25-81d3-43ce-b267-189440240415","resolution":{"observed_at":"2026-08-02T20:42:07.973187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.00210","last_updated":"2019-11-01T20:35:28Z","snapshot_observed_at":"2026-08-14T17:36:09.834261Z","submitted_at":"2019-01-01T21:17:21Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.00210","snapshot_observed_at":"2026-08-03T09:55:57.097421Z","title":"arXiv preprint arXiv:1901.00210 , year=","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2607.29294","last_updated":"2026-07-31T11:12:31Z","snapshot_observed_at":"2026-08-13T20:34:15.935730Z","submitted_at":"2026-07-31T11:12:31Z","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-03T09:55:57.097421Z"},"links":{"cited_paper":"/paper/1901.00210","citing_paper":"/paper/2607.29294"},"observation_digest":"sha256:eac79e503328cb3268a6101b8a8a3f4aa86e9cfe3e1115fab718db00e0f88f4e","observation_id":"ee2d9232-b4ba-489f-8d9f-c54ebef1d4d5","resolution":{"observed_at":"2026-08-03T09:55:57.097421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1901.00210/citation-record","integrity":"/paper/1901.00210/integrity","json":"/paper/1901.00210/citation-record.json","paper":"/paper/1901.00210"},"outbound":[],"paper":{"arxiv_id":"1901.00210","last_updated":"2019-11-01T20:35:28Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T17:36:09.834261Z","submitted_at":"2019-01-01T21:17:21Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1901.00210."}