{"as_of":"2026-08-12T16:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c99067257fc9780dcdc6465924d826bf117e0bb6265909ede8dfc5cd15d9b8a8","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T22:19:16.633815Z","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":"2026-05-18T00:46:56.898522Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.15512","last_updated":"2023-03-01T13:37:28Z","snapshot_observed_at":"2026-08-10T21:11:56.498944Z","submitted_at":"2022-05-31T02:50:17Z","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","version":2},"cited_work":{"arxiv_id":"2205.15512","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.15512","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2205.15512 , year=","venue":null,"work_id":"6f784732-cb0b-4d81-bb39-84b3dcd178a5","year":null},"citing_paper":{"arxiv_id":"2304.06767","last_updated":"2023-12-01T14:28:06Z","snapshot_observed_at":"2026-08-07T04:02:54.504761Z","submitted_at":"2023-04-13T18:22:40Z","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","version":4},"reference_index":146,"source":"arxiv_source","source_observed_at":"2026-05-18T00:46:56.664582Z"},"links":{"cited_paper":"/paper/2205.15512","citing_paper":"/paper/2304.06767"},"observation_digest":"sha256:b633868736fa9deb25d6bf12b268062f14373330c87abe41c8a8237987a1f5c2","observation_id":"382081da-3859-46bc-9a29-9abde3d635a0","resolution":{"observed_at":"2026-05-18T00:46:56.900693Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15512","last_updated":"2023-03-01T13:37:28Z","snapshot_observed_at":"2026-08-10T21:11:56.498944Z","submitted_at":"2022-05-31T02:50:17Z","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15512","snapshot_observed_at":"2026-08-10T22:19:16.633815Z","title":"Nearly minimax optimal offline rein- forcement learning with linear function approximation: Single- agent mdp and markov game.arXiv preprint arXiv:2205.15512, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.02089","last_updated":"2025-01-03T20:27:53Z","snapshot_observed_at":"2026-08-10T22:12:17.645322Z","submitted_at":"2025-01-03T20:27:53Z","title":"On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-10T22:19:16.633815Z"},"links":{"cited_paper":"/paper/2205.15512","citing_paper":"/paper/2501.02089"},"observation_digest":"sha256:c2494b1305c7e31947370046dab04c2ba24711f52132d35391691e48b3dfb46b","observation_id":"6064c2ed-6b28-489a-8a2b-74a6bfba6e3b","resolution":{"observed_at":"2026-08-10T22:19:16.633815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15512","last_updated":"2023-03-01T13:37:28Z","snapshot_observed_at":"2026-08-10T21:11:56.498944Z","submitted_at":"2022-05-31T02:50:17Z","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","version":2},"cited_work":{"arxiv_id":"2205.15512","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.15512","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2205.15512 , year=","venue":null,"work_id":"6f784732-cb0b-4d81-bb39-84b3dcd178a5","year":null},"citing_paper":{"arxiv_id":"2605.09214","last_updated":"2026-05-09T23:17:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-09T23:17:46Z","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-12T03:47:14.379908Z"},"links":{"cited_paper":"/paper/2205.15512","citing_paper":"/paper/2605.09214"},"observation_digest":"sha256:773b20426eae23a10303e270f49a0a114125971253004fe9056696e6f5be605b","observation_id":"30c3f43a-616f-48f8-8cfe-bfa15c203d48","resolution":{"observed_at":"2026-05-12T06:56:30.838377Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.15512/citation-record","integrity":"/paper/2205.15512/integrity","json":"/paper/2205.15512/citation-record.json","paper":"/paper/2205.15512"},"outbound":[],"paper":{"arxiv_id":"2205.15512","last_updated":"2023-03-01T13:37:28Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T21:11:56.498944Z","submitted_at":"2022-05-31T02:50:17Z","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2205.15512."}