{"as_of":"2026-08-11T16:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25c56f01a42ddac9443bc792d4d10bb9609406fcfeba7ecea586eb9c2ae5d0ea","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T16:18:17.390316Z","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":"2026-06-29T14:43:30.928674Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.06366","last_updated":"2020-02-19T06:05:39Z","snapshot_observed_at":"2026-08-07T06:08:50.758806Z","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.06366","snapshot_observed_at":"2026-08-10T16:18:17.390316Z","title":"Provably efficient reinforcement learning with aggregated states","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2501.13394","last_updated":"2025-06-15T19:49:41Z","snapshot_observed_at":"2026-08-11T05:35:29.939153Z","submitted_at":"2025-01-23T05:37:33Z","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T16:18:17.390316Z"},"links":{"cited_paper":"/paper/1912.06366","citing_paper":"/paper/2501.13394"},"observation_digest":"sha256:ada55d1c197051bffb30b3fe840af8fc00b4e92b50200290964ba8bc8ad3a459","observation_id":"6b58b1e7-c05e-43d9-bd33-fbb2f0f2c266","resolution":{"observed_at":"2026-08-10T16:18:17.390316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06366","last_updated":"2020-02-19T06:05:39Z","snapshot_observed_at":"2026-08-07T06:08:50.758806Z","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States","version":2},"cited_work":{"arxiv_id":"1912.06366","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.06366","snapshot_observed_at":"2026-06-29T14:43:30.928674Z","title":"Reinforcement learning with long short-term memory","venue":null,"work_id":"ebbe034c-f934-4739-8c1b-04aa3c3357ee","year":2001},"citing_paper":{"arxiv_id":"2605.00654","last_updated":"2026-05-01T13:36:46Z","snapshot_observed_at":"2026-08-02T09:28:52.427870Z","submitted_at":"2026-05-01T13:36:46Z","title":"Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-09T19:46:05.682918Z"},"links":{"cited_paper":"/paper/1912.06366","citing_paper":"/paper/2605.00654"},"observation_digest":"sha256:665262f6f79d806f0850fba426084b952ec94a4d364298f1b743cc342adfa3a3","observation_id":"52561f18-4157-4938-a0b7-cc7beb33b490","resolution":{"observed_at":"2026-05-11T15:31:19.235397Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06366","last_updated":"2020-02-19T06:05:39Z","snapshot_observed_at":"2026-08-07T06:08:50.758806Z","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States","version":2},"cited_work":{"arxiv_id":"1912.06366","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.06366","snapshot_observed_at":"2026-06-29T14:43:30.928674Z","title":"Reinforcement learning with long short-term memory","venue":null,"work_id":"ebbe034c-f934-4739-8c1b-04aa3c3357ee","year":2001},"citing_paper":{"arxiv_id":"2605.28276","last_updated":"2026-07-31T15:51:24Z","snapshot_observed_at":"2026-08-05T23:14:26.995772Z","submitted_at":"2026-05-27T10:20:40Z","title":"Commit to the Bit: Reactive Reinforcement Learning Done Right","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T14:35:28.375400Z"},"links":{"cited_paper":"/paper/1912.06366","citing_paper":"/paper/2605.28276"},"observation_digest":"sha256:619928f5744c4e6422fba10b48bb8061d2a4088fdc30eb7fdaae0c95963efee5","observation_id":"7115f0fa-2545-4a70-a185-8c1f024623ac","resolution":{"observed_at":"2026-06-29T14:43:30.930108Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06366","last_updated":"2020-02-19T06:05:39Z","snapshot_observed_at":"2026-08-07T06:08:50.758806Z","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.06366","snapshot_observed_at":"2026-08-03T02:23:32.975755Z","title":"Reinforcement learning with long short-term memory","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2605.28276","last_updated":"2026-07-31T15:51:24Z","snapshot_observed_at":"2026-08-05T23:14:26.995772Z","submitted_at":"2026-05-27T10:20:40Z","title":"Commit to the Bit: Reactive Reinforcement Learning Done Right","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-03T02:23:32.975755Z"},"links":{"cited_paper":"/paper/1912.06366","citing_paper":"/paper/2605.28276"},"observation_digest":"sha256:3ce0d1373b0efe512925b13f3caa3d66c94d2b969768d01c8e53e58e12136977","observation_id":"0f2a81c2-87bc-4dbd-b6a4-e75fd4216a41","resolution":{"observed_at":"2026-08-03T02:23:32.975755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1912.06366/citation-record","integrity":"/paper/1912.06366/integrity","json":"/paper/1912.06366/citation-record.json","paper":"/paper/1912.06366"},"outbound":[],"paper":{"arxiv_id":"1912.06366","last_updated":"2020-02-19T06:05:39Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-07T06:08:50.758806Z","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1912.06366."}