{"as_of":"2026-08-11T14:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9fc737fe3f8ccc4958aa87e2e7f5550fbea2e112dfea26b54234f1a2c04e7770","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":"2026-08-11T06:34:44.6726+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":"2026-08-09T23:14:36.801616Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.00056","snapshot_observed_at":"2026-08-09T23:14:36.801616Z","title":"and Peters, J","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.18537","last_updated":"2025-06-12T18:32:30Z","snapshot_observed_at":"2026-08-10T23:27:04.829060Z","submitted_at":"2025-01-30T18:06:18Z","title":"Loss Functions and Operators Generated by f-Divergences","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T23:14:36.801616Z"},"links":{"cited_paper":"/paper/1801.00056","citing_paper":"/paper/2501.18537"},"observation_digest":"sha256:ca8b59f12a9894eb3ab83861de50796b3716da898b5715629b2789a80d5f6d01","observation_id":"655598c2-131d-422c-909e-da34d9ee448e","resolution":{"observed_at":"2026-08-09T23:14:36.801616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"sha256:47f614aa2f6cb42c76ed082e7cb53087a7b4bd1773b780278c58615cf33fa6e5","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 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1801.00056."}