{"as_of":"2026-08-11T00:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a9a1f9b0261b2ae4dd81bee26229d8f4ff842fbb4312ade5f4d2c5ddeedf7648","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T11:07:29.249223Z","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":"2026-08-07T11:07:30.257846Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.03902","last_updated":"2025-01-07T16:10:09Z","snapshot_observed_at":"2026-08-10T21:42:27.196716Z","submitted_at":"2025-01-07T16:10:09Z","title":"Explainable Reinforcement Learning via Temporal Policy Decomposition","version":1},"cited_work":{"arxiv_id":"2501.03902","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.03902","snapshot_observed_at":"2026-08-07T11:07:30.257846Z","title":"Explainable Reinforcement Learning via Temporal Policy Decomposition","venue":"cs.LG","work_id":"159675e4-6fdc-4ac5-8442-35ee2df6cd6c","year":2025},"citing_paper":{"arxiv_id":"2506.03469","last_updated":"2025-06-04T00:54:01Z","snapshot_observed_at":"2026-08-09T11:01:55.326469Z","submitted_at":"2025-06-04T00:54:01Z","title":"Verification-Guided Falsification for Safe RL via Explainable Abstraction and Risk-Aware Exploration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:07:29.249223Z"},"links":{"cited_paper":"/paper/2501.03902","citing_paper":"/paper/2506.03469"},"observation_digest":"sha256:50243390f88b24f162067e3e98137a3bc4060c95940ca55bd9f7022e955e68fa","observation_id":"298d9481-14ae-4a21-ba95-d0e78502b63a","resolution":{"observed_at":"2026-08-07T11:07:30.264400Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.03902/citation-record","integrity":"/paper/2501.03902/integrity","json":"/paper/2501.03902/citation-record.json","paper":"/paper/2501.03902"},"outbound":[],"paper":{"arxiv_id":"2501.03902","last_updated":"2025-01-07T16:10:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T21:42:27.196716Z","submitted_at":"2025-01-07T16:10:09Z","title":"Explainable Reinforcement Learning via Temporal Policy Decomposition"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2501.03902."}