{"as_of":"2026-08-17T07:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d6e214618d7ca174ea41239e32bb680cce135ccba4349a45ebedf39009b649e","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":"2026-08-17T06:30:58.91139+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":"2026-08-10T20:13:57.638508Z","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":"2026-08-10T20:13:57.864076Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.03327","last_updated":"2020-06-23T12:45:09Z","snapshot_observed_at":"2026-07-06T08:55:52.355754Z","submitted_at":"2020-02-09T09:50:07Z","title":"Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons","version":2},"cited_work":{"arxiv_id":"2002.03327","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.03327","snapshot_observed_at":"2026-08-10T20:13:57.864076Z","title":"Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons","venue":"cs.LG","work_id":"39ef5e6d-fba4-4cbe-a793-954756875b31","year":2020},"citing_paper":{"arxiv_id":"2501.09080","last_updated":"2025-08-05T14:35:10Z","snapshot_observed_at":"2026-08-13T04:32:34.139354Z","submitted_at":"2025-01-15T19:00:46Z","title":"Average-Reward Soft Actor-Critic","version":2},"reference_index":1999,"source":"pdf_text","source_observed_at":"2026-08-10T20:13:57.638508Z"},"links":{"cited_paper":"/paper/2002.03327","citing_paper":"/paper/2501.09080"},"observation_digest":"sha256:a3d22fa59f5c6db0863630a67c21a5a131526955c73bff51c0973976ce32fef5","observation_id":"255b3875-7684-45df-b7fc-a09b7b8aa4b3","resolution":{"observed_at":"2026-08-10T20:13:57.873267Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2002.03327/citation-record","integrity":"/paper/2002.03327/integrity","json":"/paper/2002.03327/citation-record.json","paper":"/paper/2002.03327"},"outbound":[],"paper":{"arxiv_id":"2002.03327","last_updated":"2020-06-23T12:45:09Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T08:55:52.355754Z","submitted_at":"2020-02-09T09:50:07Z","title":"Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2002.03327."}