{"as_of":"2026-08-21T11:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6c876e72892ddbc225f6abbef7761533c8d14a36059d7a91cce5a9d01690397f","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":"2026-08-21T06:32:19.484+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":"2026-08-14T14:25:39.540027Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-14T14:25:39.744855Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1801.03326","last_updated":"2020-05-02T07:20:30Z","snapshot_observed_at":"2026-08-17T09:10:04.869132Z","submitted_at":"2018-01-10T11:59:59Z","title":"Expected Policy Gradients for Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"1801.03326","doi":null,"metadata_source":"pith","pith_arxiv_id":"1801.03326","snapshot_observed_at":"2026-08-14T14:25:39.744855Z","title":"Expected Policy Gradients for Reinforcement Learning","venue":"stat.ML","work_id":"9782d341-bc6f-4930-a929-27e6a3d326b1","year":2018},"citing_paper":{"arxiv_id":"1908.03263","last_updated":"2019-08-08T20:35:53Z","snapshot_observed_at":"2026-08-18T07:30:05.983534Z","submitted_at":"2019-08-08T20:35:53Z","title":"Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:25:39.540027Z"},"links":{"cited_paper":"/paper/1801.03326","citing_paper":"/paper/1908.03263"},"observation_digest":"sha256:92a72c425f1ecab06a4bbaaf606412a49ef568c92a285ba88942c83c04dcc2c1","observation_id":"9627ad71-871a-4bb5-8b6f-3f4df6e5262a","resolution":{"observed_at":"2026-08-14T14:25:39.759551Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1801.03326/citation-record","integrity":"/paper/1801.03326/integrity","json":"/paper/1801.03326/citation-record.json","paper":"/paper/1801.03326"},"outbound":[],"paper":{"arxiv_id":"1801.03326","last_updated":"2020-05-02T07:20:30Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-17T09:10:04.869132Z","submitted_at":"2018-01-10T11:59:59Z","title":"Expected Policy Gradients 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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1801.03326."}