{"as_of":"2026-08-08T14:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8bb3d3df8ad05c778db7e03004079b64fcdfe83920202d41316e6b418a8ff0c","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T12:43:48.515394Z","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":"2026-07-04T13:09:51.302063Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.01289","last_updated":"2020-06-29T16:09:49Z","snapshot_observed_at":"2026-08-08T13:28:57.729025Z","submitted_at":"2019-08-04T07:51:36Z","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01289","snapshot_observed_at":"2026-08-07T12:43:48.515394Z","title":"Novoseller, Yanan Sui, Yisong Yue, and Joel W","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.23927","last_updated":"2025-05-29T18:22:02Z","snapshot_observed_at":"2026-08-07T12:35:50.981783Z","submitted_at":"2025-05-29T18:22:02Z","title":"Thompson Sampling in Online RLHF with General Function Approximation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:43:48.515394Z"},"links":{"cited_paper":"/paper/1908.01289","citing_paper":"/paper/2505.23927"},"observation_digest":"sha256:f6c6e9907b16da1109c4e93c5ba6eb9521f1a4eb7672fae9c0f1c8084e86f08c","observation_id":"99e536a6-804c-4e8e-9d7d-6a8133fa2060","resolution":{"observed_at":"2026-08-07T12:43:48.515394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01289","last_updated":"2020-06-29T16:09:49Z","snapshot_observed_at":"2026-08-08T13:28:57.729025Z","submitted_at":"2019-08-04T07:51:36Z","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","version":4},"cited_work":{"arxiv_id":"1908.01289","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.01289","snapshot_observed_at":"2026-07-04T13:09:51.302063Z","title":"1029–1038, PMLR, 2020, arXiv:1908.012892","venue":null,"work_id":"75563d9a-f935-40c6-9024-226694275ec4","year":2020},"citing_paper":{"arxiv_id":"2606.27082","last_updated":"2026-06-25T14:20:03Z","snapshot_observed_at":"2026-08-07T21:42:58.159964Z","submitted_at":"2026-06-25T14:20:03Z","title":"Finding Stationary Points by Comparisons","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-26T05:26:07.720218Z"},"links":{"cited_paper":"/paper/1908.01289","citing_paper":"/paper/2606.27082"},"observation_digest":"sha256:8b5f10946f913448a29d56d9847c515e7ac32a27f9d963de07e1de10f2b62e82","observation_id":"2c4d08ec-b37c-43e1-b5d5-8834b378f028","resolution":{"observed_at":"2026-07-04T13:09:51.303516Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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/1908.01289/citation-record","integrity":"/paper/1908.01289/integrity","json":"/paper/1908.01289/citation-record.json","paper":"/paper/1908.01289"},"outbound":[],"paper":{"arxiv_id":"1908.01289","last_updated":"2020-06-29T16:09:49Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T13:28:57.729025Z","submitted_at":"2019-08-04T07:51:36Z","title":"Dueling Posterior Sampling for 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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1908.01289."}