{"as_of":"2026-08-22T13:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b4b30ee1f2fdba9867b84d294714f7ec5932a0754a71fb7a27296cc567127338","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":"2026-08-22T06:32:14.747728+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":"2026-08-12T20:29:36.055043Z","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":"2026-05-22T13:01:34.207516Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2003.07337","last_updated":"2020-03-16T17:15:28Z","snapshot_observed_at":"2026-08-13T18:03:48.268549Z","submitted_at":"2020-03-16T17:15:28Z","title":"Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.07337","snapshot_observed_at":"2026-08-12T20:29:36.055043Z","title":"Khamaru, A","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2411.09731","last_updated":"2024-11-27T23:19:41Z","snapshot_observed_at":"2026-08-20T03:23:45.934123Z","submitted_at":"2024-11-14T19:00:00Z","title":"To bootstrap or to rollout? An optimal and adaptive interpolation","version":2},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-12T20:29:36.055043Z"},"links":{"cited_paper":"/paper/2003.07337","citing_paper":"/paper/2411.09731"},"observation_digest":"sha256:c5d77987bdee68deb4db01191933c1cae6f61512b71a54453636412e684e4f04","observation_id":"dd8b8f6c-ffbf-4a33-8c15-f65bc1ab43e0","resolution":{"observed_at":"2026-08-12T20:29:36.055043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.07337","last_updated":"2020-03-16T17:15:28Z","snapshot_observed_at":"2026-08-13T18:03:48.268549Z","submitted_at":"2020-03-16T17:15:28Z","title":"Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis","version":1},"cited_work":{"arxiv_id":"2003.07337","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.07337","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Is temporal difference learning optimal? an instance-dependent analysis","venue":null,"work_id":"c25cc882-4edf-40f6-b080-fba96d041645","year":2003},"citing_paper":{"arxiv_id":"2509.08933","last_updated":"2026-05-21T17:37:36Z","snapshot_observed_at":"2026-08-18T15:35:48.669340Z","submitted_at":"2025-09-10T18:56:39Z","title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-22T12:58:26.626172Z"},"links":{"cited_paper":"/paper/2003.07337","citing_paper":"/paper/2509.08933"},"observation_digest":"sha256:8bff019197dc8485b92ed395f41f7036b4a5362576558cc3d398301b6a0ad388","observation_id":"63783f68-f6cd-4297-9eae-eb7aa1caaef0","resolution":{"observed_at":"2026-05-22T13:01:34.210762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2003.07337/citation-record","integrity":"/paper/2003.07337/integrity","json":"/paper/2003.07337/citation-record.json","paper":"/paper/2003.07337"},"outbound":[],"paper":{"arxiv_id":"2003.07337","last_updated":"2020-03-16T17:15:28Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-13T18:03:48.268549Z","submitted_at":"2020-03-16T17:15:28Z","title":"Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2003.07337."}