{"as_of":"2026-08-19T23:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6e2fb6847a52d1d14d19ff67120eaf293bdc725400abbe386d3992d3a114e3c0","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":"2026-08-19T06:32:44.657259+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":"2026-08-15T22:39:59.288557Z","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":"2026-05-23T21:53:29.871025Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.11104","last_updated":"2022-05-23T07:54:15Z","snapshot_observed_at":"2026-08-19T05:46:08.876473Z","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":"2205.11104","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.11104","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Generalization, mayhems and limits in recurrent proximal policy op- timization","venue":null,"work_id":"4f2a1c12-85e0-4db6-a7e1-6d5ecd73bc84","year":2022},"citing_paper":{"arxiv_id":"2408.09468","last_updated":"2026-04-03T23:17:12Z","snapshot_observed_at":"2026-08-17T15:19:45.833896Z","submitted_at":"2024-08-18T13:27:49Z","title":"Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control Framework","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-23T21:49:48.432653Z"},"links":{"cited_paper":"/paper/2205.11104","citing_paper":"/paper/2408.09468"},"observation_digest":"sha256:316d7bda9d846eea9fc811c0510dc62981ec02f8595050449308a481d814f8e6","observation_id":"d0d29ce9-41e8-4787-be93-d8d6d358c1df","resolution":{"observed_at":"2026-05-23T21:53:29.873940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11104","last_updated":"2022-05-23T07:54:15Z","snapshot_observed_at":"2026-08-19T05:46:08.876473Z","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11104","snapshot_observed_at":"2026-08-09T15:32:47.793071Z","title":"Generalization, mayhems and limits in recurrent proximal policy op- timization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01387","last_updated":"2025-02-20T14:09:01Z","snapshot_observed_at":"2026-08-15T23:13:36.293817Z","submitted_at":"2025-02-03T14:22:03Z","title":"TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T15:32:47.793071Z"},"links":{"cited_paper":"/paper/2205.11104","citing_paper":"/paper/2502.01387"},"observation_digest":"sha256:6ab86d55196a28115e0f0dee4af3448875b3d27e2e875338d10703c437f34517","observation_id":"95749692-a54a-4d73-9f4c-a63ba8ce0c19","resolution":{"observed_at":"2026-08-09T15:32:47.793071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11104","last_updated":"2022-05-23T07:54:15Z","snapshot_observed_at":"2026-08-19T05:46:08.876473Z","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11104","snapshot_observed_at":"2026-08-15T22:39:59.288557Z","title":"Generalization, mayhems and limits in recurrent proximal policy optimization, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06744","last_updated":"2025-05-10T19:36:18Z","snapshot_observed_at":"2026-08-19T21:44:36.096756Z","submitted_at":"2025-05-10T19:36:18Z","title":"LineFlow: A Framework to Learn Active Control of Production Lines","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T22:39:59.288557Z"},"links":{"cited_paper":"/paper/2205.11104","citing_paper":"/paper/2505.06744"},"observation_digest":"sha256:065dac84230dfa541beae0cd5ee6430f47e8c831d2b4c935feac723b21c2bef5","observation_id":"23f34723-89e1-4ea1-be3d-89a487f61372","resolution":{"observed_at":"2026-08-15T22:39:59.288557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11104","last_updated":"2022-05-23T07:54:15Z","snapshot_observed_at":"2026-08-19T05:46:08.876473Z","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11104","snapshot_observed_at":"2026-08-01T16:29:17.810844Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18001","last_updated":"2026-07-20T14:33:47Z","snapshot_observed_at":"2026-08-17T14:52:18.229967Z","submitted_at":"2026-07-20T14:33:47Z","title":"AlphaZeroBeta: Deep Reinforcement Learning for Market-Neutral Portfolios","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T16:29:17.810844Z"},"links":{"cited_paper":"/paper/2205.11104","citing_paper":"/paper/2607.18001"},"observation_digest":"sha256:25e389d42cc5b806bc56cfa8f904b55215c7de483fb26b716e212be6a8224699","observation_id":"f0b3eba1-e541-40b8-acf5-7f0a83d65a48","resolution":{"observed_at":"2026-08-01T16:29:17.810844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2205.11104/citation-record","integrity":"/paper/2205.11104/integrity","json":"/paper/2205.11104/citation-record.json","paper":"/paper/2205.11104"},"outbound":[],"paper":{"arxiv_id":"2205.11104","last_updated":"2022-05-23T07:54:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T05:46:08.876473Z","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2205.11104."}