{"as_of":"2026-08-08T22:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3cea5a3130ef233137ff3bafdb822588e4f1027929bda254fc2543a08c725e22","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":"2026-08-07T12:43:47.660403Z","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":"2026-07-04T13:09:51.305130Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.11140","last_updated":"2022-05-24T02:42:19Z","snapshot_observed_at":"2026-08-08T03:49:48.218596Z","submitted_at":"2022-05-23T09:03:24Z","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11140","snapshot_observed_at":"2026-08-07T12:43:47.660403Z","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation.arXiv e-prints, page arXiv:2205.11140, May 2022","venue":null,"work_id":null,"year":2022},"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":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:43:47.660403Z"},"links":{"cited_paper":"/paper/2205.11140","citing_paper":"/paper/2505.23927"},"observation_digest":"sha256:fdc720bbf5527e07ada586db85ce82d6340b00d8c5cb71e100a11e41e054e676","observation_id":"bf60b172-58a5-4b1c-a562-17d5db2b54ab","resolution":{"observed_at":"2026-08-07T12:43:47.660403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11140","last_updated":"2022-05-24T02:42:19Z","snapshot_observed_at":"2026-08-08T03:49:48.218596Z","submitted_at":"2022-05-23T09:03:24Z","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","version":2},"cited_work":{"arxiv_id":"2205.11140","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.11140","snapshot_observed_at":"2026-07-04T13:09:51.305130Z","title":"3773–3793, PMLR, 2022, arXiv:2205.11140 2","venue":null,"work_id":"7c701acc-d25a-4c08-be47-023724df1116","year":2022},"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":10,"source":"pdf_text","source_observed_at":"2026-06-26T05:26:07.720218Z"},"links":{"cited_paper":"/paper/2205.11140","citing_paper":"/paper/2606.27082"},"observation_digest":"sha256:13f84a60455891e45a88bcafb449bbff33f502cd09eb79762af98d767b3b5f36","observation_id":"57e59c0f-f7ed-4906-ad64-af922c89c8ca","resolution":{"observed_at":"2026-07-04T13:09:51.306394Z","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/2205.11140/citation-record","integrity":"/paper/2205.11140/integrity","json":"/paper/2205.11140/citation-record.json","paper":"/paper/2205.11140"},"outbound":[],"paper":{"arxiv_id":"2205.11140","last_updated":"2022-05-24T02:42:19Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T03:49:48.218596Z","submitted_at":"2022-05-23T09:03:24Z","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation"},"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:2205.11140."}