{"as_of":"2026-08-08T13:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7b41524bdedd0920583bccd5d7e482b70d0d8b358abd6d557e8f04aa923669e1","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:32:52.586211Z","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":"2026-08-07T00:32:55.551567Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.12174","last_updated":"2020-02-26T17:15:53Z","snapshot_observed_at":"2026-08-08T01:34:17.837088Z","submitted_at":"2020-02-26T17:15:53Z","title":"Optimistic Exploration even with a Pessimistic Initialisation","version":1},"cited_work":{"arxiv_id":"2002.12174","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.12174","snapshot_observed_at":"2026-08-07T00:32:55.551567Z","title":"Optimistic Exploration even with a Pessimistic Initialisation","venue":"cs.LG","work_id":"b83ea9e0-b8cb-4011-a6de-2db080e9984a","year":2020},"citing_paper":{"arxiv_id":"2506.13672","last_updated":"2025-06-16T16:30:00Z","snapshot_observed_at":"2026-08-07T00:25:29.162842Z","submitted_at":"2025-06-16T16:30:00Z","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T00:32:52.586211Z"},"links":{"cited_paper":"/paper/2002.12174","citing_paper":"/paper/2506.13672"},"observation_digest":"sha256:4031028f76b1f840980fff53d04d8af5e5c8251b7e142b41e4c59418cbf41701","observation_id":"ac7e3916-194d-49ab-9420-f5302e4f0da4","resolution":{"observed_at":"2026-08-07T00:32:55.555362Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.12174","last_updated":"2020-02-26T17:15:53Z","snapshot_observed_at":"2026-08-08T01:34:17.837088Z","submitted_at":"2020-02-26T17:15:53Z","title":"Optimistic Exploration even with a Pessimistic Initialisation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.12174","snapshot_observed_at":"2026-07-11T13:53:36.775836Z","title":"arXiv preprint arXiv:2002.12174 , year=","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":1},"reference_index":182,"source":"arxiv_source","source_observed_at":"2026-07-11T13:53:36.775836Z"},"links":{"cited_paper":"/paper/2002.12174","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:4a07da1dc82c3bda5503fb1519cc1bcba68c396ec49d41fb96a91d601ce84b1c","observation_id":"619cdb38-8e88-46f5-a6de-ae3aaff0ef32","resolution":{"observed_at":"2026-07-11T13:53:36.775836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.12174","last_updated":"2020-02-26T17:15:53Z","snapshot_observed_at":"2026-08-08T01:34:17.837088Z","submitted_at":"2020-02-26T17:15:53Z","title":"Optimistic Exploration even with a Pessimistic Initialisation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.12174","snapshot_observed_at":"2026-08-02T08:40:53.814178Z","title":"arXiv preprint arXiv:2002.12174 , year=","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":3},"reference_index":183,"source":"arxiv_source","source_observed_at":"2026-08-02T08:40:53.814178Z"},"links":{"cited_paper":"/paper/2002.12174","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:4c6fd58b1dc4a94d13ec3d4b76563c8f561c0c3b364ad7f0dc2c0146c68dba4d","observation_id":"e5085f2b-c684-46a5-a292-d1bfcb36a168","resolution":{"observed_at":"2026-08-02T08:40:53.814178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.12174/citation-record","integrity":"/paper/2002.12174/integrity","json":"/paper/2002.12174/citation-record.json","paper":"/paper/2002.12174"},"outbound":[],"paper":{"arxiv_id":"2002.12174","last_updated":"2020-02-26T17:15:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T01:34:17.837088Z","submitted_at":"2020-02-26T17:15:53Z","title":"Optimistic Exploration even with a Pessimistic Initialisation"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2002.12174."}