{"as_of":"2026-08-14T21:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:60a80f3a722d2638f6526b475480f3fd4c596381f258ca6511b5beb116074dda","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T05:45:00.350019Z","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":"2026-08-11T05:45:00.957610Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2009.01555","last_updated":"2021-03-17T14:43:36Z","snapshot_observed_at":"2026-08-13T21:42:12.882073Z","submitted_at":"2020-09-03T10:04:06Z","title":"Sample-Efficient Automated Deep Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2009.01555","doi":null,"metadata_source":"pith","pith_arxiv_id":"2009.01555","snapshot_observed_at":"2026-08-11T05:45:00.957610Z","title":"Sample-Efficient Automated Deep Reinforcement Learning","venue":"cs.LG","work_id":"9a577ea3-f746-47c5-99c2-e3f34fcdc497","year":2020},"citing_paper":{"arxiv_id":"2412.17256","last_updated":"2025-03-04T06:29:50Z","snapshot_observed_at":"2026-08-14T05:57:08.449467Z","submitted_at":"2024-12-23T03:58:34Z","title":"B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T05:45:00.350019Z"},"links":{"cited_paper":"/paper/2009.01555","citing_paper":"/paper/2412.17256"},"observation_digest":"sha256:9d4d7f3acd592a68c4fee814d428d65a417553b27cb66a18337c10e2b77cef58","observation_id":"9cb6829f-b254-48fb-a735-126e4665de2f","resolution":{"observed_at":"2026-08-11T05:45:00.963917Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2009.01555/citation-record","integrity":"/paper/2009.01555/integrity","json":"/paper/2009.01555/citation-record.json","paper":"/paper/2009.01555"},"outbound":[],"paper":{"arxiv_id":"2009.01555","last_updated":"2021-03-17T14:43:36Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T21:42:12.882073Z","submitted_at":"2020-09-03T10:04:06Z","title":"Sample-Efficient Automated Deep 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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2009.01555."}