{"as_of":"2026-08-12T19:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dcd3658bfd321049c8f65891811a7855311b741fc3fac79f7075de3acd872a6a","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":"2026-08-11T00:10:22.373621Z","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":"2026-05-20T14:08:21.042363Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.04044","last_updated":"2024-02-26T15:18:31Z","snapshot_observed_at":"2026-08-04T18:55:04.998004Z","submitted_at":"2022-06-08T17:58:06Z","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04044","snapshot_observed_at":"2026-08-11T00:10:22.373621Z","title":"Model-base d reinforcement learning is minimax-optimal for offline zero-sum markov games","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19873","last_updated":"2024-12-27T16:37:33Z","snapshot_observed_at":"2026-08-10T23:53:11.923237Z","submitted_at":"2024-12-27T16:37:33Z","title":"Minimax-Optimal Multi-Agent Robust Reinforcement Learning","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-11T00:10:22.373621Z"},"links":{"cited_paper":"/paper/2206.04044","citing_paper":"/paper/2412.19873"},"observation_digest":"sha256:c4e074ff6f9a389ee4f4774d506ee2b409b7b05508615893a79e47ddd35d5c7b","observation_id":"ddeba19e-c782-45bc-ad07-ea24804a82ec","resolution":{"observed_at":"2026-08-11T00:10:22.373621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04044","last_updated":"2024-02-26T15:18:31Z","snapshot_observed_at":"2026-08-04T18:55:04.998004Z","submitted_at":"2022-06-08T17:58:06Z","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","version":2},"cited_work":{"arxiv_id":"2206.04044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.04044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2206.04044 , year=","venue":null,"work_id":"bb5e83d6-1fae-4de7-babd-eee25a2d16d2","year":null},"citing_paper":{"arxiv_id":"2605.03393","last_updated":"2026-05-05T06:08:54Z","snapshot_observed_at":"2026-08-07T11:17:36.866995Z","submitted_at":"2026-05-05T06:08:54Z","title":"Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity","version":1},"reference_index":238,"source":"arxiv_source","source_observed_at":"2026-05-07T13:27:05.081050Z"},"links":{"cited_paper":"/paper/2206.04044","citing_paper":"/paper/2605.03393"},"observation_digest":"sha256:1491e5af22947d545714da9b45d19c0632032c3f0635222f336e8ffbeb820472","observation_id":"b57408f3-7b46-41e3-a3c6-0b48980d9709","resolution":{"observed_at":"2026-05-12T08:56:26.449188Z","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":"2206.04044","last_updated":"2024-02-26T15:18:31Z","snapshot_observed_at":"2026-08-04T18:55:04.998004Z","submitted_at":"2022-06-08T17:58:06Z","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games","version":2},"cited_work":{"arxiv_id":"2206.04044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.04044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2206.04044 , year=","venue":null,"work_id":"bb5e83d6-1fae-4de7-babd-eee25a2d16d2","year":null},"citing_paper":{"arxiv_id":"2605.17189","last_updated":"2026-06-09T02:46:33Z","snapshot_observed_at":"2026-08-02T14:26:15.767422Z","submitted_at":"2026-05-16T23:10:10Z","title":"Sample-efficient inductive matrix completion with noise and inexact side-information","version":1},"reference_index":165,"source":"arxiv_source","source_observed_at":"2026-05-20T14:04:44.364824Z"},"links":{"cited_paper":"/paper/2206.04044","citing_paper":"/paper/2605.17189"},"observation_digest":"sha256:ee1d55383f53a4d5cb17841b01ee86dcda2967a324e4974b81f7df90971833a8","observation_id":"95adf0a4-71de-4d93-929f-16dcb8e4c6bd","resolution":{"observed_at":"2026-05-20T14:08:21.043940Z","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/2206.04044/citation-record","integrity":"/paper/2206.04044/integrity","json":"/paper/2206.04044/citation-record.json","paper":"/paper/2206.04044"},"outbound":[],"paper":{"arxiv_id":"2206.04044","last_updated":"2024-02-26T15:18:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T18:55:04.998004Z","submitted_at":"2022-06-08T17:58:06Z","title":"Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games"},"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:2206.04044."}