{"as_of":"2026-08-15T02:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:103d10248eac3c386564ad83227070c083d4c0eb0732be140f3fb0fa47cd148a","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":"2026-08-14T06:32:32.682623+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":"2026-08-09T00:08:08.503214Z","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":"2026-07-03T23:29:02.935467Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.07637","last_updated":"2024-05-14T08:10:15Z","snapshot_observed_at":"2026-08-13T00:09:01.836123Z","submitted_at":"2024-05-13T10:51:01Z","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07637","snapshot_observed_at":"2026-08-09T00:08:08.503214Z","title":"Cassel, H","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04004","last_updated":"2025-02-06T12:03:24Z","snapshot_observed_at":"2026-08-14T14:10:02.451899Z","submitted_at":"2025-02-06T12:03:24Z","title":"Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T00:08:08.503214Z"},"links":{"cited_paper":"/paper/2405.07637","citing_paper":"/paper/2502.04004"},"observation_digest":"sha256:8e028ff5dd4ac766f13990687cc4ffd5d6069ec25c7ea3c390f322e6873a926e","observation_id":"699927c1-cb2f-4ee0-9007-a75377c529d0","resolution":{"observed_at":"2026-08-09T00:08:08.503214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07637","last_updated":"2024-05-14T08:10:15Z","snapshot_observed_at":"2026-08-13T00:09:01.836123Z","submitted_at":"2024-05-13T10:51:01Z","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07637","snapshot_observed_at":"2026-08-07T14:10:39.669228Z","title":"Near-optimal regret in linear mdps with aggregate bandit feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","snapshot_observed_at":"2026-08-12T03:05:25.202458Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T14:10:39.669228Z"},"links":{"cited_paper":"/paper/2405.07637","citing_paper":"/paper/2505.20268"},"observation_digest":"sha256:b99cd5d6ee87c9d47f68a9d4961b3e77feece0ff4853aca6421d78df13412628","observation_id":"8998aaef-1560-4dc3-926c-2f66599e2a49","resolution":{"observed_at":"2026-08-07T14:10:39.669228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07637","last_updated":"2024-05-14T08:10:15Z","snapshot_observed_at":"2026-08-13T00:09:01.836123Z","submitted_at":"2024-05-13T10:51:01Z","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","version":2},"cited_work":{"arxiv_id":"2405.07637","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.07637","snapshot_observed_at":"2026-07-03T23:29:02.935467Z","title":"arXiv preprint arXiv:2405.07637 , year=","venue":null,"work_id":"25fa5f07-8332-43e2-87fe-07d94829411f","year":null},"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":73,"source":"arxiv_source","source_observed_at":"2026-06-26T22:06:24.412259Z"},"links":{"cited_paper":"/paper/2405.07637","citing_paper":"/paper/2606.18531"},"observation_digest":"sha256:3ae873ae93808e6ffe319f2d0f10f13c423e06ae73a6227f78cd5ea4c956ab5c","observation_id":"2235d6ee-d481-4f4f-9947-cf2a99a962ec","resolution":{"observed_at":"2026-07-03T23:29:02.936716Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.07637/citation-record","integrity":"/paper/2405.07637/integrity","json":"/paper/2405.07637/citation-record.json","paper":"/paper/2405.07637"},"outbound":[],"paper":{"arxiv_id":"2405.07637","last_updated":"2024-05-14T08:10:15Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T00:09:01.836123Z","submitted_at":"2024-05-13T10:51:01Z","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.07637."}