{"as_of":"2026-08-16T14:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9fb4705791b00e4f9d40a11c50366abcf81f4deafc2b1c9bb9f291448288c33b","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T14:39:15.496949Z","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":"2026-07-04T08:49:42.823741Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.03760","last_updated":"2020-12-01T09:14:25Z","snapshot_observed_at":"2026-08-16T12:10:02.540006Z","submitted_at":"2020-07-07T19:44:14Z","title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2007.03760","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.03760","snapshot_observed_at":"2026-07-04T08:49:42.823741Z","title":"arXiv preprint arXiv:2007.03760 , year=","venue":null,"work_id":"2ea173ff-1e1e-4e44-8194-9ed687b7fad5","year":2007},"citing_paper":{"arxiv_id":"2606.22579","last_updated":"2026-06-21T16:29:25Z","snapshot_observed_at":"2026-08-02T07:11:59.062207Z","submitted_at":"2026-06-21T16:29:25Z","title":"Stationary Robust Mean-Field Games under Model Mismatches","version":1},"reference_index":213,"source":"arxiv_source","source_observed_at":"2026-06-26T10:50:40.841967Z"},"links":{"cited_paper":"/paper/2007.03760","citing_paper":"/paper/2606.22579"},"observation_digest":"sha256:87c4a67754cc575395b9891a7a419a4d423d9de40c72c028e6f37c1c585db119","observation_id":"93e4b668-f261-4d02-bd9f-1d723ca8b680","resolution":{"observed_at":"2026-07-04T08:49:42.825214Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.03760","last_updated":"2020-12-01T09:14:25Z","snapshot_observed_at":"2026-08-16T12:10:02.540006Z","submitted_at":"2020-07-07T19:44:14Z","title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03760","snapshot_observed_at":"2026-08-15T14:39:15.496949Z","title":"arXiv preprint arXiv:2007.03760 , year=","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2608.06545","last_updated":"2026-08-06T19:49:48Z","snapshot_observed_at":"2026-08-16T06:31:47.673457Z","submitted_at":"2026-08-06T19:49:48Z","title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T14:39:15.496949Z"},"links":{"cited_paper":"/paper/2007.03760","citing_paper":"/paper/2608.06545"},"observation_digest":"sha256:c2b0cb4dec13b0be87f9b28fe40dc3c4baa09fd516fbc4ca9790f6884b105593","observation_id":"791b6d3f-07a0-4b23-b368-86e548e84c4f","resolution":{"observed_at":"2026-08-15T14:39:15.496949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2007.03760/citation-record","integrity":"/paper/2007.03760/integrity","json":"/paper/2007.03760/citation-record.json","paper":"/paper/2007.03760"},"outbound":[],"paper":{"arxiv_id":"2007.03760","last_updated":"2020-12-01T09:14:25Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T12:10:02.540006Z","submitted_at":"2020-07-07T19:44:14Z","title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for 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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2007.03760."}