{"as_of":"2026-08-13T23:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4b8a6ad111dd00e9920a7374d7eb58eb2fc70ad5c0e241d42bfc04ada771d759","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T18:11:48.413795Z","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":"2026-08-10T17:04:32.003686Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.03236","last_updated":"2023-06-05T20:45:30Z","snapshot_observed_at":"2026-08-13T11:23:55.874235Z","submitted_at":"2023-06-05T20:45:30Z","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03236","snapshot_observed_at":"2026-08-10T18:11:48.413795Z","title":"arXiv preprint arXiv:2306.03236 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.11533","last_updated":"2025-01-20T15:17:24Z","snapshot_observed_at":"2026-08-13T08:28:50.646600Z","submitted_at":"2025-01-20T15:17:24Z","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T18:11:48.413795Z"},"links":{"cited_paper":"/paper/2306.03236","citing_paper":"/paper/2501.11533"},"observation_digest":"sha256:40069488dd57a2f141ccb01b9f3defbe69596d8e426f3d74a1f86bfdf232825a","observation_id":"5da5c150-2693-492c-b481-8fe33dace0e3","resolution":{"observed_at":"2026-08-10T18:11:48.413795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03236","last_updated":"2023-06-05T20:45:30Z","snapshot_observed_at":"2026-08-13T11:23:55.874235Z","submitted_at":"2023-06-05T20:45:30Z","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","version":1},"cited_work":{"arxiv_id":"2306.03236","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.03236","snapshot_observed_at":"2026-08-10T17:04:32.003686Z","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","venue":"cs.AI","work_id":"de895682-d243-4c93-b2e6-072034ff0879","year":2023},"citing_paper":{"arxiv_id":"2501.12627","last_updated":"2025-01-22T04:22:13Z","snapshot_observed_at":"2026-08-12T12:18:59.926921Z","submitted_at":"2025-01-22T04:22:13Z","title":"Deep Reinforcement Learning with Hybrid Intrinsic Reward Model","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T17:04:31.760641Z"},"links":{"cited_paper":"/paper/2306.03236","citing_paper":"/paper/2501.12627"},"observation_digest":"sha256:45fc16b9212ba7cc32bc230dab49a900d6d43df8956766dd852707113d8e531e","observation_id":"ecdcb10c-28dd-4b67-8e33-85840a9f89e1","resolution":{"observed_at":"2026-08-10T17:04:32.011275Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2306.03236/citation-record","integrity":"/paper/2306.03236/integrity","json":"/paper/2306.03236/citation-record.json","paper":"/paper/2306.03236"},"outbound":[],"paper":{"arxiv_id":"2306.03236","last_updated":"2023-06-05T20:45:30Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-13T11:23:55.874235Z","submitted_at":"2023-06-05T20:45:30Z","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.03236."}