{"as_of":"2026-08-05T12:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b118aa582c2e1d60d23dfa2b17e2b36e184a9714da76d8bdd9222293cdcc9c2f","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":"2026-08-05T06:32:48.257954+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":"2026-08-04T00:53:27.989253Z","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":"2003.14089","last_updated":"2021-01-06T14:12:57Z","snapshot_observed_at":"2026-08-05T04:41:53.389161Z","submitted_at":"2020-03-31T10:55:06Z","title":"Leverage the Average: an Analysis of KL Regularization in RL","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14089","snapshot_observed_at":"2026-07-14T23:47:45.866615Z","title":"Leverage the average: an analysis of kl regularization in rl.arXiv preprint arXiv:2003.14089, 2020","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2603.10250","last_updated":"2026-05-24T03:43:13Z","snapshot_observed_at":"2026-07-14T23:47:43.007890Z","submitted_at":"2026-03-10T22:01:13Z","title":"GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T23:47:45.866615Z"},"links":{"cited_paper":"/paper/2003.14089","citing_paper":"/paper/2603.10250"},"observation_digest":"sha256:4d40c74c0f5bef0cd7c17ad7571629c7ecf0d5b09a27b8897ea1f0e042b5f1be","observation_id":"fa639a5d-d1df-4de3-b211-77a8127240ce","resolution":{"observed_at":"2026-07-14T23:47:45.866615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14089","last_updated":"2021-01-06T14:12:57Z","snapshot_observed_at":"2026-08-05T04:41:53.389161Z","submitted_at":"2020-03-31T10:55:06Z","title":"Leverage the Average: an Analysis of KL Regularization in RL","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14089","snapshot_observed_at":"2026-08-04T00:53:27.989253Z","title":"Leverage the Average: an Analysis of","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2608.00301","last_updated":"2026-07-31T21:31:07Z","snapshot_observed_at":"2026-08-05T12:24:03.851045Z","submitted_at":"2026-07-31T21:31:07Z","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T00:53:27.989253Z"},"links":{"cited_paper":"/paper/2003.14089","citing_paper":"/paper/2608.00301"},"observation_digest":"sha256:f2ec7bb725fa16ca363346b513052780941ff13f7c72b90609dbb0f12b1d046f","observation_id":"352f964e-166d-4f4f-8e61-4f50a47f5763","resolution":{"observed_at":"2026-08-04T00:53:27.989253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2003.14089/citation-record","integrity":"/paper/2003.14089/integrity","json":"/paper/2003.14089/citation-record.json","paper":"/paper/2003.14089"},"outbound":[],"paper":{"arxiv_id":"2003.14089","last_updated":"2021-01-06T14:12:57Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T04:41:53.389161Z","submitted_at":"2020-03-31T10:55:06Z","title":"Leverage the Average: an Analysis of KL Regularization in RL"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2003.14089."}