{"as_of":"2026-08-08T18:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bdbf8d4c717feab964f28fd545a1dcc2e75368e7a5b4afd03fb02e5c52c8664f","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T13:03:54.976956Z","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":"2026-05-17T01:48:50.988888Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.05767","last_updated":"2023-12-28T20:16:50Z","snapshot_observed_at":"2026-07-06T13:40:55.365861Z","submitted_at":"2022-08-11T11:55:31Z","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.05767","snapshot_observed_at":"2026-08-07T13:03:54.976956Z","title":"Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23003","last_updated":"2025-05-29T02:25:13Z","snapshot_observed_at":"2026-08-07T12:53:14.202052Z","submitted_at":"2025-05-29T02:25:13Z","title":"Hybrid Cross-domain Robust Reinforcement Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:54.976956Z"},"links":{"cited_paper":"/paper/2208.05767","citing_paper":"/paper/2505.23003"},"observation_digest":"sha256:df88c6ed58387a04cca590efc2a351e06cae151a82cc8630680212ec28db2c51","observation_id":"c8cd894a-0807-4521-b6a3-3d3e495534f1","resolution":{"observed_at":"2026-08-07T13:03:54.976956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05767","last_updated":"2023-12-28T20:16:50Z","snapshot_observed_at":"2026-07-06T13:40:55.365861Z","submitted_at":"2022-08-11T11:55:31Z","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","version":4},"cited_work":{"arxiv_id":"2208.05767","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.05767","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, and Dong Yu","venue":null,"work_id":"acd9653d-eba4-4dbe-b485-d11ace29c564","year":null},"citing_paper":{"arxiv_id":"2512.03847","last_updated":"2026-05-06T14:15:19Z","snapshot_observed_at":"2026-08-03T04:49:11.537109Z","submitted_at":"2025-12-03T14:48:38Z","title":"DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-17T01:46:21.744857Z"},"links":{"cited_paper":"/paper/2208.05767","citing_paper":"/paper/2512.03847"},"observation_digest":"sha256:4c65b358c332e774e51e7a54de359fe05b89ce098b3b446613e4d7d75ca1924d","observation_id":"723e80d0-6fe5-46e9-aee9-dafd5bfdba2a","resolution":{"observed_at":"2026-05-17T01:48:50.992508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05767","last_updated":"2023-12-28T20:16:50Z","snapshot_observed_at":"2026-07-06T13:40:55.365861Z","submitted_at":"2022-08-11T11:55:31Z","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","version":4},"cited_work":{"arxiv_id":"2208.05767","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.05767","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, and Dong Yu","venue":null,"work_id":"acd9653d-eba4-4dbe-b485-d11ace29c564","year":null},"citing_paper":{"arxiv_id":"2605.03125","last_updated":"2026-05-06T22:03:28Z","snapshot_observed_at":"2026-08-04T04:13:10.377270Z","submitted_at":"2026-05-04T20:04:52Z","title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-08T19:13:15.234351Z"},"links":{"cited_paper":"/paper/2208.05767","citing_paper":"/paper/2605.03125"},"observation_digest":"sha256:38fccb0ac2c29ee449025a9c37293badd679e341d24dba9ae01ca4f22f437367","observation_id":"562ea72f-78db-420d-8cd5-1d8f81f07aea","resolution":{"observed_at":"2026-05-09T06:00:35.978178Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2208.05767/citation-record","integrity":"/paper/2208.05767/integrity","json":"/paper/2208.05767/citation-record.json","paper":"/paper/2208.05767"},"outbound":[],"paper":{"arxiv_id":"2208.05767","last_updated":"2023-12-28T20:16:50Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T13:40:55.365861Z","submitted_at":"2022-08-11T11:55:31Z","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2208.05767."}