{"as_of":"2026-08-11T03:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7680f24b12f3713e6e8b60ea8bc440dddd336414a23ee40e5ea013da9aaaf07f","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":"2026-08-10T06:31:04.303077+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":"2026-08-05T16:38:02.783901Z","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":"2026-08-05T16:38:03.609545Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.00857","last_updated":"2020-04-02T08:05:18Z","snapshot_observed_at":"2026-08-10T19:24:07.067512Z","submitted_at":"2020-04-02T08:05:18Z","title":"Average Reward Adjusted Discounted Reinforcement Learning: Near-Blackwell-Optimal Policies for Real-World Applications","version":1},"cited_work":{"arxiv_id":"2004.00857","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.00857","snapshot_observed_at":"2026-08-05T16:38:03.609545Z","title":"Average Reward Adjusted Discounted Reinforcement Learning: Near-Blackwell-Optimal Policies for Real-World Applications","venue":"cs.LG","work_id":"3b195ecc-873a-4fe6-a07d-3f38231ab84d","year":2020},"citing_paper":{"arxiv_id":"2508.18252","last_updated":"2025-08-25T17:41:30Z","snapshot_observed_at":"2026-08-10T18:06:26.853512Z","submitted_at":"2025-08-25T17:41:30Z","title":"Efficient Computation of Blackwell Optimal Policies using Rational Functions","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T16:38:02.783901Z"},"links":{"cited_paper":"/paper/2004.00857","citing_paper":"/paper/2508.18252"},"observation_digest":"sha256:fbbdb3de1e81f4b33cd1ff1ac1d40ecaa5c28714d26896f74e749cecba3d9a0e","observation_id":"620941bf-78fc-46ec-a09d-9d888cf26580","resolution":{"observed_at":"2026-08-05T16:38:03.691073Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2004.00857/citation-record","integrity":"/paper/2004.00857/integrity","json":"/paper/2004.00857/citation-record.json","paper":"/paper/2004.00857"},"outbound":[],"paper":{"arxiv_id":"2004.00857","last_updated":"2020-04-02T08:05:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T19:24:07.067512Z","submitted_at":"2020-04-02T08:05:18Z","title":"Average Reward Adjusted Discounted Reinforcement Learning: Near-Blackwell-Optimal Policies for Real-World Applications"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2004.00857."}