{"as_of":"2026-08-17T07:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2c77313db9c568fb383f0fa452fe7796ba8e56313b3c97307ba1bddbcd050f2f","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":"2026-08-15T19:38:50.959942Z","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":"2026-08-15T19:38:51.197671Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.10081","last_updated":"2022-01-25T03:48:00Z","snapshot_observed_at":"2026-08-16T17:26:13.400175Z","submitted_at":"2022-01-25T03:48:00Z","title":"Dynamics-Aware Comparison of Learned Reward Functions","version":1},"cited_work":{"arxiv_id":"2201.10081","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.10081","snapshot_observed_at":"2026-08-15T19:38:51.197671Z","title":"Dynamics-Aware Comparison of Learned Reward Functions","venue":"cs.LG","work_id":"0a3dc8b9-dd10-4ad3-a3e0-5975cae5195a","year":2022},"citing_paper":{"arxiv_id":"2506.15421","last_updated":"2025-06-18T12:46:39Z","snapshot_observed_at":"2026-08-16T17:35:22.013765Z","submitted_at":"2025-06-18T12:46:39Z","title":"Reward Models in Deep Reinforcement Learning: A Survey","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T19:38:50.959942Z"},"links":{"cited_paper":"/paper/2201.10081","citing_paper":"/paper/2506.15421"},"observation_digest":"sha256:a90f4e2650627d9dade4caa9fcf4ed641c0ac8af7c3f8785d07c2dba389b17ab","observation_id":"5f0cf442-4de2-42dd-a4a1-b515064d66f3","resolution":{"observed_at":"2026-08-15T19:38:51.286313Z","resolver_source":"local_arxiv","status":"verified_exact"},"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/2201.10081/citation-record","integrity":"/paper/2201.10081/integrity","json":"/paper/2201.10081/citation-record.json","paper":"/paper/2201.10081"},"outbound":[],"paper":{"arxiv_id":"2201.10081","last_updated":"2022-01-25T03:48:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T17:26:13.400175Z","submitted_at":"2022-01-25T03:48:00Z","title":"Dynamics-Aware Comparison of Learned Reward Functions"},"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 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2201.10081."}