{"as_of":"2026-08-09T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9d09c69938ec533380489df09579e28b88fd1fa7bade6a60a0570a15745b6a2d","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":"2026-08-07T12:12:57.547010Z","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":"2026-08-07T12:13:01.656376Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.04190","last_updated":"2024-08-08T03:18:42Z","snapshot_observed_at":"2026-08-09T05:53:00.468066Z","submitted_at":"2024-08-08T03:18:42Z","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2408.04190","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.04190","snapshot_observed_at":"2026-08-07T12:13:01.656376Z","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","venue":"cs.LG","work_id":"ccfe2d4c-d4ff-4e0f-ad7b-2724526bc851","year":2024},"citing_paper":{"arxiv_id":"2506.00388","last_updated":"2025-06-10T13:10:39Z","snapshot_observed_at":"2026-08-09T05:52:49.452533Z","submitted_at":"2025-05-31T04:37:07Z","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T12:12:57.547010Z"},"links":{"cited_paper":"/paper/2408.04190","citing_paper":"/paper/2506.00388"},"observation_digest":"sha256:7c8d7ef4f741960245404158692e674903de35dc916b289f7fab1832d648adbb","observation_id":"c9248b55-c092-436d-9845-69455364ba71","resolution":{"observed_at":"2026-08-07T12:13:01.753321Z","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/2408.04190/citation-record","integrity":"/paper/2408.04190/integrity","json":"/paper/2408.04190/citation-record.json","paper":"/paper/2408.04190"},"outbound":[],"paper":{"arxiv_id":"2408.04190","last_updated":"2024-08-08T03:18:42Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T05:53:00.468066Z","submitted_at":"2024-08-08T03:18:42Z","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2408.04190."}