{"as_of":"2026-08-08T23:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:74d8b5c3247a5ee563d1c4442ca068a1f72da71e6e9a4887ff1dac29efc11474","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":"2026-08-07T15:19:08.152208Z","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":"2026-08-07T15:19:10.539429Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.15568","last_updated":"2024-07-09T12:04:03Z","snapshot_observed_at":"2026-07-06T18:35:13.166449Z","submitted_at":"2024-06-21T18:06:30Z","title":"Robust Reinforcement Learning from Corrupted Human Feedback","version":2},"cited_work":{"arxiv_id":"2406.15568","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.15568","snapshot_observed_at":"2026-08-07T15:19:10.539429Z","title":"Robust Reinforcement Learning from Corrupted Human Feedback","venue":"cs.LG","work_id":"12f8d326-8ad6-41d2-a08f-ebe34fcc16de","year":2024},"citing_paper":{"arxiv_id":"2505.15694","last_updated":"2025-05-21T16:07:47Z","snapshot_observed_at":"2026-08-08T05:51:01.468645Z","submitted_at":"2025-05-21T16:07:47Z","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","version":1},"reference_index":1952,"source":"pdf_text","source_observed_at":"2026-08-07T15:19:08.152208Z"},"links":{"cited_paper":"/paper/2406.15568","citing_paper":"/paper/2505.15694"},"observation_digest":"sha256:6cda69d52e06028d273c53723c8d23f5cdc4c7d78df7058b2c529cc4a46a08d1","observation_id":"791c3347-9199-4ea2-90c8-b9eb91a052ad","resolution":{"observed_at":"2026-08-07T15:19:10.582859Z","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/2406.15568/citation-record","integrity":"/paper/2406.15568/integrity","json":"/paper/2406.15568/citation-record.json","paper":"/paper/2406.15568"},"outbound":[],"paper":{"arxiv_id":"2406.15568","last_updated":"2024-07-09T12:04:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:35:13.166449Z","submitted_at":"2024-06-21T18:06:30Z","title":"Robust Reinforcement Learning from Corrupted Human Feedback"},"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:2406.15568."}