{"as_of":"2026-08-07T07:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d40fa0f4106e36e1a8b23e3267832924ddf1abaed4363d3609990e6c1aa30260","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T12:37:47.941595Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.04840","last_updated":"2024-10-03T16:23:07Z","snapshot_observed_at":"2026-08-05T12:18:43.626181Z","submitted_at":"2024-09-07T14:38:05Z","title":"Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04840","snapshot_observed_at":"2026-08-04T12:37:47.941595Z","title":"Sample and oracle efficient reinforcement learning for mdps with linearly-realizable value functions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.03494","last_updated":"2026-05-31T00:15:42Z","snapshot_observed_at":"2026-08-04T12:37:45.532870Z","submitted_at":"2025-10-03T20:18:35Z","title":"Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\\pi$-Realizability and Concentrability","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T12:37:47.941595Z"},"links":{"cited_paper":"/paper/2409.04840","citing_paper":"/paper/2510.03494"},"observation_digest":"sha256:560918c015a57db700abc6b8127cc3bd90dee6c52de2233458de24f5de590f43","observation_id":"96ece97d-2dd6-4469-9d6f-de5a07d6b671","resolution":{"observed_at":"2026-08-04T12:37:47.941595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.04840/citation-record","integrity":"/paper/2409.04840/integrity","json":"/paper/2409.04840/citation-record.json","paper":"/paper/2409.04840"},"outbound":[],"paper":{"arxiv_id":"2409.04840","last_updated":"2024-10-03T16:23:07Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T12:18:43.626181Z","submitted_at":"2024-09-07T14:38:05Z","title":"Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions"},"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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2409.04840."}