{"as_of":"2026-08-16T18:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4b762826a92a75620f6b23c8bbf670d6c561040e6e101f6c383d861bb4606a24","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":"2026-08-16T06:30:59.297886+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":"2026-08-03T09:55:52.528190Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.02794","last_updated":"2020-02-07T14:03:38Z","snapshot_observed_at":"2026-08-13T22:24:42.320362Z","submitted_at":"2020-02-07T14:03:38Z","title":"Reward-Free Exploration for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.02794","snapshot_observed_at":"2026-08-03T09:55:52.528190Z","title":"arXiv:2002.02794 , year =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.29294","last_updated":"2026-07-31T11:12:31Z","snapshot_observed_at":"2026-08-13T20:34:15.935730Z","submitted_at":"2026-07-31T11:12:31Z","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-03T09:55:52.528190Z"},"links":{"cited_paper":"/paper/2002.02794","citing_paper":"/paper/2607.29294"},"observation_digest":"sha256:27372086c002ca190bb8010034673c4e2f8d2073efd6defc3ea79ce1d205862b","observation_id":"6be6006c-4c81-4d3a-aba0-c51c18fbbee8","resolution":{"observed_at":"2026-08-03T09:55:52.528190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.02794/citation-record","integrity":"/paper/2002.02794/integrity","json":"/paper/2002.02794/citation-record.json","paper":"/paper/2002.02794"},"outbound":[],"paper":{"arxiv_id":"2002.02794","last_updated":"2020-02-07T14:03:38Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T22:24:42.320362Z","submitted_at":"2020-02-07T14:03:38Z","title":"Reward-Free Exploration for 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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2002.02794."}