{"as_of":"2026-08-08T01:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9064c0d403536921f5b199e448e11642e6fc22c2ef8a0f756d823ecfd3c59d77","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T18:26:19.003008Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T23:29:02.946204Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.03744","last_updated":"2023-12-19T01:22:47Z","snapshot_observed_at":"2026-07-06T10:02:30.383493Z","submitted_at":"2020-10-08T03:07:31Z","title":"Maximum Reward Formulation In Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03744","snapshot_observed_at":"2026-08-06T18:26:19.003008Z","title":"Maximum reward formulation in reinforcement learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08537","last_updated":"2025-09-04T05:12:57Z","snapshot_observed_at":"2026-08-06T19:38:57.971145Z","submitted_at":"2025-07-11T12:37:20Z","title":"Recursive Reward Aggregation","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T18:26:19.003008Z"},"links":{"cited_paper":"/paper/2010.03744","citing_paper":"/paper/2507.08537"},"observation_digest":"sha256:e62c8fd69db8db7c2c13d3cfefc8c0a2808870fbd9c22ef62f4e9067dad22d8e","observation_id":"49ddf05e-1189-4f76-a303-5ccc80dee85c","resolution":{"observed_at":"2026-08-06T18:26:19.003008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03744","last_updated":"2023-12-19T01:22:47Z","snapshot_observed_at":"2026-07-06T10:02:30.383493Z","submitted_at":"2020-10-08T03:07:31Z","title":"Maximum Reward Formulation In Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2010.03744","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.03744","snapshot_observed_at":"2026-07-03T23:29:02.946204Z","title":"arXiv preprint arXiv:2010.03744 , year=","venue":null,"work_id":"22554688-1976-4110-9fe9-097637d74c2a","year":2010},"citing_paper":{"arxiv_id":"2606.18531","last_updated":"2026-06-16T22:55:45Z","snapshot_observed_at":"2026-08-04T10:57:17.249083Z","submitted_at":"2026-06-16T22:55:45Z","title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-06-26T22:06:24.412259Z"},"links":{"cited_paper":"/paper/2010.03744","citing_paper":"/paper/2606.18531"},"observation_digest":"sha256:cfd6d47c5ac39b53350d350e7c0b6c473e2ebb34b9dfab881abada333ca66c43","observation_id":"7974386d-d0e6-47e0-8402-d53e4cd7811a","resolution":{"observed_at":"2026-07-03T23:29:02.947516Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2010.03744/citation-record","integrity":"/paper/2010.03744/integrity","json":"/paper/2010.03744/citation-record.json","paper":"/paper/2010.03744"},"outbound":[],"paper":{"arxiv_id":"2010.03744","last_updated":"2023-12-19T01:22:47Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:02:30.383493Z","submitted_at":"2020-10-08T03:07:31Z","title":"Maximum Reward Formulation In 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2010.03744."}