{"as_of":"2026-08-12T17:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1b01de17c1723e468079f94fba67c017d4f8ef938ad4e66e81cbec131753f203","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T14:19:32.296024Z","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":"2026-05-20T12:48:17.525703Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2202.00082","last_updated":"2023-02-15T11:50:24Z","snapshot_observed_at":"2026-08-12T12:40:11.465152Z","submitted_at":"2022-01-31T20:39:48Z","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.00082","snapshot_observed_at":"2026-08-11T14:19:32.296024Z","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.12326","last_updated":"2025-06-16T11:10:31Z","snapshot_observed_at":"2026-08-11T14:10:24.030150Z","submitted_at":"2024-12-16T19:44:44Z","title":"Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T14:19:32.296024Z"},"links":{"cited_paper":"/paper/2202.00082","citing_paper":"/paper/2412.12326"},"observation_digest":"sha256:1d1e6543ae0abbfcd676d94804decbdb9bd5a53f0a42ca27736b8a0d8e325533","observation_id":"c0b50ea6-9c0c-4f96-a4c6-36b7c6a2bd3b","resolution":{"observed_at":"2026-08-11T14:19:32.296024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00082","last_updated":"2023-02-15T11:50:24Z","snapshot_observed_at":"2026-08-12T12:40:11.465152Z","submitted_at":"2022-01-31T20:39:48Z","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","version":3},"cited_work":{"arxiv_id":"2202.00082","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.00082","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2202.00082 , year=","venue":null,"work_id":"97dbbc2e-a2d0-4e8c-a3b8-0f9e282f4f5c","year":null},"citing_paper":{"arxiv_id":"2605.18591","last_updated":"2026-08-03T00:43:51Z","snapshot_observed_at":"2026-08-06T23:24:40.850221Z","submitted_at":"2026-05-18T16:05:36Z","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","version":1},"reference_index":127,"source":"arxiv_source","source_observed_at":"2026-05-20T12:44:29.147095Z"},"links":{"cited_paper":"/paper/2202.00082","citing_paper":"/paper/2605.18591"},"observation_digest":"sha256:26c36696dde31ecdcf2dcfe44f7e7eaf06a15b9108880ba8c161acd7191d48e4","observation_id":"0f741d6d-13ef-47d3-b7e1-86d50650257f","resolution":{"observed_at":"2026-05-20T12:48:17.527345Z","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/2202.00082/citation-record","integrity":"/paper/2202.00082/integrity","json":"/paper/2202.00082/citation-record.json","paper":"/paper/2202.00082"},"outbound":[],"paper":{"arxiv_id":"2202.00082","last_updated":"2023-02-15T11:50:24Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T12:40:11.465152Z","submitted_at":"2022-01-31T20:39:48Z","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity"},"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 2 inbound Pith citation observations for arXiv:2202.00082."}