{"as_of":"2026-08-08T14:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7eb836bf28e936209f760497e773a447677f17506eb490f1d2ae98648b6ed20b","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T21:34:28.208406Z","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":"2026-05-15T05:09:45.458685Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09574","last_updated":"2025-05-16T04:56:04Z","snapshot_observed_at":"2026-07-06T18:30:41.802045Z","submitted_at":"2024-06-13T20:25:52Z","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09574","snapshot_observed_at":"2026-08-05T21:34:28.208406Z","title":"Online bandit learning with offline preference data.arXiv preprint arXiv:2406.09574,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.08413","last_updated":"2025-08-11T19:07:30Z","snapshot_observed_at":"2026-08-07T12:16:45.804784Z","submitted_at":"2025-08-11T19:07:30Z","title":"Decentralized Relaxed Smooth Optimization with Gradient Descent Methods","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-05T21:34:28.208406Z"},"links":{"cited_paper":"/paper/2406.09574","citing_paper":"/paper/2508.08413"},"observation_digest":"sha256:743e20dcf5590f20992252eabf5e37663cc2c7aec67892185ca625975ae0ecf0","observation_id":"999b1d41-92d8-4b78-9603-c90c16f0dd28","resolution":{"observed_at":"2026-08-05T21:34:28.208406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09574","last_updated":"2025-05-16T04:56:04Z","snapshot_observed_at":"2026-07-06T18:30:41.802045Z","submitted_at":"2024-06-13T20:25:52Z","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09574","snapshot_observed_at":"2026-08-05T16:17:24.627733Z","title":"Online bandit learning with offline preference data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18841","last_updated":"2025-08-26T09:18:13Z","snapshot_observed_at":"2026-08-08T09:45:09.523122Z","submitted_at":"2025-08-26T09:18:13Z","title":"Recycling History: Efficient Recommendations from Contextual Dueling Bandits","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T16:17:24.627733Z"},"links":{"cited_paper":"/paper/2406.09574","citing_paper":"/paper/2508.18841"},"observation_digest":"sha256:18bf273673f8af0ca4a9dc0ca27dfff8c71f9e4a7fea360b0f95f1d4ff4689c0","observation_id":"07d2f385-b721-4694-a546-bb97cddd2e63","resolution":{"observed_at":"2026-08-05T16:17:24.627733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09574","last_updated":"2025-05-16T04:56:04Z","snapshot_observed_at":"2026-07-06T18:30:41.802045Z","submitted_at":"2024-06-13T20:25:52Z","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","version":4},"cited_work":{"arxiv_id":"2406.09574","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09574","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.09574 , year=","venue":null,"work_id":"8a995226-b5c4-4732-94e8-51d6181c712f","year":null},"citing_paper":{"arxiv_id":"2605.10289","last_updated":"2026-05-14T09:25:47Z","snapshot_observed_at":"2026-07-06T23:22:18.704329Z","submitted_at":"2026-05-11T09:50:58Z","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-12T04:41:20.147645Z"},"links":{"cited_paper":"/paper/2406.09574","citing_paper":"/paper/2605.10289"},"observation_digest":"sha256:86d6bda4878378eb131f132101385c7507c1bcaf89457ef710013c309c5304fb","observation_id":"74a4b375-fb97-4186-8367-cdd78afc8c23","resolution":{"observed_at":"2026-05-12T06:01:24.959000Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09574","last_updated":"2025-05-16T04:56:04Z","snapshot_observed_at":"2026-07-06T18:30:41.802045Z","submitted_at":"2024-06-13T20:25:52Z","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","version":4},"cited_work":{"arxiv_id":"2406.09574","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09574","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.09574 , year=","venue":null,"work_id":"8a995226-b5c4-4732-94e8-51d6181c712f","year":null},"citing_paper":{"arxiv_id":"2605.10289","last_updated":"2026-05-14T09:25:47Z","snapshot_observed_at":"2026-07-06T23:22:18.704329Z","submitted_at":"2026-05-11T09:50:58Z","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-15T05:07:34.344964Z"},"links":{"cited_paper":"/paper/2406.09574","citing_paper":"/paper/2605.10289"},"observation_digest":"sha256:6a4737c2f22e22beb625f83e5c36ad8ebd746338b6bae64f489000a2ca6a28dc","observation_id":"acaf2133-be61-4a56-bfa0-463827a3ce7a","resolution":{"observed_at":"2026-05-15T05:09:45.462565Z","resolver_source":"arxiv_id","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/2406.09574/citation-record","integrity":"/paper/2406.09574/integrity","json":"/paper/2406.09574/citation-record.json","paper":"/paper/2406.09574"},"outbound":[],"paper":{"arxiv_id":"2406.09574","last_updated":"2025-05-16T04:56:04Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:30:41.802045Z","submitted_at":"2024-06-13T20:25:52Z","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF"},"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 4 inbound Pith citation observations for arXiv:2406.09574."}