{"as_of":"2026-08-04T05:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7f9a13929e1b50e545fc32efff31a2296c61ab29bd4d9ca867c3bf1c65eb07eb","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":"2026-08-03T06:30:56.289259+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":"2026-05-11T01:13:29.292351Z","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":"2026-05-11T04:35:58.759274Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1801.00056","last_updated":"2018-04-04T11:36:12Z","snapshot_observed_at":"2026-07-06T06:16:35.445115Z","submitted_at":"2017-12-29T23:07:26Z","title":"f-Divergence constrained policy improvement","version":2},"cited_work":{"arxiv_id":"1801.00056","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1801.00056","snapshot_observed_at":"2026-07-04T22:40:26.761367Z","title":"Bradley, R","venue":null,"work_id":"0fe5b0e9-1c0e-4bbc-8351-f970533733e2","year":null},"citing_paper":{"arxiv_id":"2605.06977","last_updated":"2026-05-07T21:48:26Z","snapshot_observed_at":"2026-07-06T23:19:25.538514Z","submitted_at":"2026-05-07T21:48:26Z","title":"$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-11T01:13:29.292351Z"},"links":{"cited_paper":"/paper/1801.00056","citing_paper":"/paper/2605.06977"},"observation_digest":"sha256:55e1ebb35959f84be68b7e4643d7f5236a69bf76ccc09138e2b34e14890782bc","observation_id":"1dfab8b9-57b3-467d-b395-6e1c56a7c561","resolution":{"observed_at":"2026-07-04T22:40:26.761367Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1801.00056/citation-record","integrity":"/paper/1801.00056/integrity","json":"/paper/1801.00056/citation-record.json","paper":"/paper/1801.00056"},"outbound":[],"paper":{"arxiv_id":"1801.00056","last_updated":"2018-04-04T11:36:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T06:16:35.445115Z","submitted_at":"2017-12-29T23:07:26Z","title":"f-Divergence constrained policy improvement"},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1801.00056."}