{"as_of":"2026-08-08T07:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83c5cfc82ef1b5f38db4c126d17c2ef88d86b051cc61f95b0df983a98133a08a","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":"2026-08-07T14:01:05.568274Z","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":"2026-08-07T14:01:08.101786Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.05434","last_updated":"2025-08-08T03:36:58Z","snapshot_observed_at":"2026-07-06T20:33:11.256513Z","submitted_at":"2025-02-08T03:47:00Z","title":"Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling","version":3},"cited_work":{"arxiv_id":"2502.05434","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.05434","snapshot_observed_at":"2026-08-07T14:01:08.101786Z","title":"Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling","venue":"cs.LG","work_id":"bd3c668e-b165-43e9-b401-bb3fe5f0d4de","year":2025},"citing_paper":{"arxiv_id":"2505.20556","last_updated":"2025-05-26T22:34:42Z","snapshot_observed_at":"2026-08-07T13:49:33.928724Z","submitted_at":"2025-05-26T22:34:42Z","title":"Learning a Pessimistic Reward Model in RLHF","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T14:01:05.568274Z"},"links":{"cited_paper":"/paper/2502.05434","citing_paper":"/paper/2505.20556"},"observation_digest":"sha256:2e4f9ad593d355e83583d2745469fed801389d27561b226e55aeab60beb76bce","observation_id":"301e7a58-e6e9-434e-9935-0ccf2266b1bf","resolution":{"observed_at":"2026-08-07T14:01:08.191682Z","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/2502.05434/citation-record","integrity":"/paper/2502.05434/integrity","json":"/paper/2502.05434/citation-record.json","paper":"/paper/2502.05434"},"outbound":[],"paper":{"arxiv_id":"2502.05434","last_updated":"2025-08-08T03:36:58Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:33:11.256513Z","submitted_at":"2025-02-08T03:47:00Z","title":"Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling"},"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:2502.05434."}