{"as_of":"2026-08-18T00:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17dd24297a280bb5c618f40d4d5c325cf83f7e9ab818b7cc93dbed4b48399176","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:35:59.627958Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T18:35:59.918644Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2202.12742","last_updated":"2022-05-10T13:05:58Z","snapshot_observed_at":"2026-08-17T12:53:58.877626Z","submitted_at":"2022-02-23T07:21:44Z","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2202.12742","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.12742","snapshot_observed_at":"2026-08-12T18:35:59.918644Z","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning","venue":"cs.LG","work_id":"ef71614a-5271-4cb9-ace0-e19bfef20cf2","year":2022},"citing_paper":{"arxiv_id":"2411.11457","last_updated":"2024-11-18T10:44:20Z","snapshot_observed_at":"2026-08-17T09:25:13.586799Z","submitted_at":"2024-11-18T10:44:20Z","title":"Upside-Down Reinforcement Learning for More Interpretable Optimal Control","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T18:35:59.627958Z"},"links":{"cited_paper":"/paper/2202.12742","citing_paper":"/paper/2411.11457"},"observation_digest":"sha256:7fc8943f497aef56cdd371a39987caa34cfedfe78c23eca8dddf773bbbdbd3a3","observation_id":"d8711a58-671b-4cde-9fb0-e2c312369abd","resolution":{"observed_at":"2026-08-12T18:35:59.922846Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2202.12742/citation-record","integrity":"/paper/2202.12742/integrity","json":"/paper/2202.12742/citation-record.json","paper":"/paper/2202.12742"},"outbound":[],"paper":{"arxiv_id":"2202.12742","last_updated":"2022-05-10T13:05:58Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T12:53:58.877626Z","submitted_at":"2022-02-23T07:21:44Z","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2202.12742."}