{"as_of":"2026-08-14T08:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6a74aa08864d94eab5a97ba787549815a997aab0797e6c71ac067095067369c6","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":"2026-08-14T06:32:32.682623+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":"2026-08-05T05:09:29.215472Z","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":"2026-05-13T07:59:56.016347Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.09575","last_updated":"2021-03-17T11:34:54Z","snapshot_observed_at":"2026-07-06T10:50:44.662873Z","submitted_at":"2021-03-17T11:34:54Z","title":"Regularized Behavior Value Estimation","version":1},"cited_work":{"arxiv_id":"2103.09575","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.09575","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gulcehre, S","venue":null,"work_id":"5b72772c-d609-4855-b70c-39243c310edc","year":null},"citing_paper":{"arxiv_id":"2308.08998","last_updated":"2023-08-21T10:23:42Z","snapshot_observed_at":"2026-08-13T14:38:32.919809Z","submitted_at":"2023-08-17T14:12:48Z","title":"Reinforced Self-Training (ReST) for Language Modeling","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-13T07:59:55.849296Z"},"links":{"cited_paper":"/paper/2103.09575","citing_paper":"/paper/2308.08998"},"observation_digest":"sha256:639778040d5f6e2bd198bb121c72c9cd1049955dae365d55bfe135a3d2e3ced5","observation_id":"ca6f7041-842e-4859-b38a-ca4bc0fdb638","resolution":{"observed_at":"2026-05-13T07:59:56.018636Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09575","last_updated":"2021-03-17T11:34:54Z","snapshot_observed_at":"2026-07-06T10:50:44.662873Z","submitted_at":"2021-03-17T11:34:54Z","title":"Regularized Behavior Value Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.09575","snapshot_observed_at":"2026-08-05T05:09:29.215472Z","title":"Regularized behavior value estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05735","last_updated":"2025-09-06T14:52:33Z","snapshot_observed_at":"2026-08-13T23:58:11.604459Z","submitted_at":"2025-09-06T14:52:33Z","title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T05:09:29.215472Z"},"links":{"cited_paper":"/paper/2103.09575","citing_paper":"/paper/2509.05735"},"observation_digest":"sha256:7a5155f60262524a947360051805334c11d42eb4eb1596e626030cd24e7ab8fa","observation_id":"86bb3937-28c7-4ce8-90fb-f09a9540103e","resolution":{"observed_at":"2026-08-05T05:09:29.215472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2103.09575/citation-record","integrity":"/paper/2103.09575/integrity","json":"/paper/2103.09575/citation-record.json","paper":"/paper/2103.09575"},"outbound":[],"paper":{"arxiv_id":"2103.09575","last_updated":"2021-03-17T11:34:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:50:44.662873Z","submitted_at":"2021-03-17T11:34:54Z","title":"Regularized Behavior Value Estimation"},"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 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2103.09575."}