{"as_of":"2026-08-08T11:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b117e02e0545beba2ca1994a8d3365774313b1f376c39df904e0e3cbbe94cdd","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T12:13:00.884525Z","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":"2026-08-07T12:13:01.313466Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.11774","last_updated":"2024-05-08T15:58:02Z","snapshot_observed_at":"2026-07-06T14:45:19.481734Z","submitted_at":"2023-01-27T15:18:54Z","title":"Reinforcement Learning from Diverse Human Preferences","version":3},"cited_work":{"arxiv_id":"2301.11774","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.11774","snapshot_observed_at":"2026-08-07T12:13:01.313466Z","title":"Reinforcement Learning from Diverse Human Preferences","venue":"cs.LG","work_id":"dc209747-9f86-444c-8789-0655b8d8bfe5","year":2023},"citing_paper":{"arxiv_id":"2506.00388","last_updated":"2025-06-10T13:10:39Z","snapshot_observed_at":"2026-08-07T15:00:04.313363Z","submitted_at":"2025-05-31T04:37:07Z","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T12:13:00.884525Z"},"links":{"cited_paper":"/paper/2301.11774","citing_paper":"/paper/2506.00388"},"observation_digest":"sha256:546bf3c51050e7e6fe95da5ba146595b153ba955c2a6f76086dcef5ae143ae74","observation_id":"38bed9a6-7783-490b-a08f-063e354bd693","resolution":{"observed_at":"2026-08-07T12:13:01.391953Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2301.11774/citation-record","integrity":"/paper/2301.11774/integrity","json":"/paper/2301.11774/citation-record.json","paper":"/paper/2301.11774"},"outbound":[],"paper":{"arxiv_id":"2301.11774","last_updated":"2024-05-08T15:58:02Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T14:45:19.481734Z","submitted_at":"2023-01-27T15:18:54Z","title":"Reinforcement Learning from Diverse Human Preferences"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2301.11774."}