{"as_of":"2026-08-10T00:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e39709c79a9997c6dbddfb19bc796b86ce6dc1d0c66156804f8b41ce64c71d1","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T21:33:36.415315Z","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":"2026-07-04T08:19:43.712345Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.10264","last_updated":"2021-12-19T21:47:04Z","snapshot_observed_at":"2026-08-06T17:21:50.888775Z","submitted_at":"2021-12-19T21:47:04Z","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10264","snapshot_observed_at":"2026-08-06T21:33:36.415315Z","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00358","last_updated":"2025-07-23T14:00:39Z","snapshot_observed_at":"2026-08-09T09:01:08.945491Z","submitted_at":"2025-07-01T01:09:06Z","title":"Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:33:36.415315Z"},"links":{"cited_paper":"/paper/2112.10264","citing_paper":"/paper/2507.00358"},"observation_digest":"sha256:9ffb0e4bf4a09893653be5788d0ee4bcb6781bc2d376e5b44f7317d726bb5608","observation_id":"8f088e2d-74bb-468c-8c19-ee4d41f8cfcc","resolution":{"observed_at":"2026-08-06T21:33:36.415315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10264","last_updated":"2021-12-19T21:47:04Z","snapshot_observed_at":"2026-08-06T17:21:50.888775Z","submitted_at":"2021-12-19T21:47:04Z","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10264","snapshot_observed_at":"2026-08-05T13:11:44.567437Z","title":"Exploration-exploitation trade-off for continuous- time episodic reinforcement learning with linear-convex models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.00904","last_updated":"2025-08-31T15:34:24Z","snapshot_observed_at":"2026-08-05T13:11:42.300909Z","submitted_at":"2025-08-31T15:34:24Z","title":"Convergence Rates of Time Discretization in Extended Mean Field Control","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T13:11:44.567437Z"},"links":{"cited_paper":"/paper/2112.10264","citing_paper":"/paper/2509.00904"},"observation_digest":"sha256:beb4605beb570129cd6b5e702615bfd34f4dee52e5304e89bd45282715a40bb3","observation_id":"3b8eb266-6736-453f-a2a2-194c4c23cfb7","resolution":{"observed_at":"2026-08-05T13:11:44.567437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10264","last_updated":"2021-12-19T21:47:04Z","snapshot_observed_at":"2026-08-06T17:21:50.888775Z","submitted_at":"2021-12-19T21:47:04Z","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","version":1},"cited_work":{"arxiv_id":"2112.10264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2112.10264","snapshot_observed_at":"2026-07-04T08:19:43.712345Z","title":"arXiv preprint arXiv:2112.10264 , year=","venue":null,"work_id":"a1b17737-7c2c-4eae-a2a3-7965213cf023","year":null},"citing_paper":{"arxiv_id":"2606.21925","last_updated":"2026-06-20T07:47:41Z","snapshot_observed_at":"2026-07-06T23:56:49.977855Z","submitted_at":"2026-06-20T07:47:41Z","title":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-06-26T11:59:18.223000Z"},"links":{"cited_paper":"/paper/2112.10264","citing_paper":"/paper/2606.21925"},"observation_digest":"sha256:cc22dd1894030c5cb1066922bf74193473ad52308eb5ddaca53473f9d1339157","observation_id":"67ff858d-e86e-46ef-bdcb-9c6803eaefde","resolution":{"observed_at":"2026-07-04T08:19:43.714245Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2112.10264/citation-record","integrity":"/paper/2112.10264/integrity","json":"/paper/2112.10264/citation-record.json","paper":"/paper/2112.10264"},"outbound":[],"paper":{"arxiv_id":"2112.10264","last_updated":"2021-12-19T21:47:04Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T17:21:50.888775Z","submitted_at":"2021-12-19T21:47:04Z","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2112.10264."}