{"as_of":"2026-08-20T00:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5086b1d83130739836affb0451212b9b9f175f81221cad53ac30eb0d6f55a2c2","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:26:27.949991Z","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":"2026-08-12T14:10:46.616356Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.12975","last_updated":"2023-10-28T21:15:07Z","snapshot_observed_at":"2026-08-16T15:13:41.574673Z","submitted_at":"2023-07-24T17:50:24Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.12975","snapshot_observed_at":"2026-08-16T11:26:27.949991Z","title":"Provable benefits of policy learning from human preferences in contextual bandit problems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.15812","last_updated":"2025-04-22T11:51:20Z","snapshot_observed_at":"2026-08-16T11:15:02.357997Z","submitted_at":"2025-04-22T11:51:20Z","title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T11:26:27.949991Z"},"links":{"cited_paper":"/paper/2307.12975","citing_paper":"/paper/2504.15812"},"observation_digest":"sha256:15b0d3b69a6617200dbe9647f868ada4e50e03428d1d78d7492effbefedb99b7","observation_id":"badb5ea3-3f00-44ec-a56a-facf1f0a8407","resolution":{"observed_at":"2026-08-16T11:26:27.949991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.12975","last_updated":"2023-10-28T21:15:07Z","snapshot_observed_at":"2026-08-16T15:13:41.574673Z","submitted_at":"2023-07-24T17:50:24Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.12975","snapshot_observed_at":"2026-08-15T14:33:57.861566Z","title":"arXiv preprint arXiv:2307.12975 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.07419","last_updated":"2026-08-07T17:05:10Z","snapshot_observed_at":"2026-08-19T11:38:58.290988Z","submitted_at":"2026-08-07T17:05:10Z","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","version":1},"reference_index":235,"source":"arxiv_source","source_observed_at":"2026-08-15T14:33:57.861566Z"},"links":{"cited_paper":"/paper/2307.12975","citing_paper":"/paper/2608.07419"},"observation_digest":"sha256:ad4dcb7f18b667961f1037557f291121a4207544a449e272bc498499c77bb74d","observation_id":"c1ddcf5e-e2d6-4180-9c18-9b1d98fc76a2","resolution":{"observed_at":"2026-08-15T14:33:57.861566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.12975","last_updated":"2023-10-28T21:15:07Z","snapshot_observed_at":"2026-08-16T15:13:41.574673Z","submitted_at":"2023-07-24T17:50:24Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","version":2},"cited_work":{"arxiv_id":"2307.12975","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.12975","snapshot_observed_at":"2026-08-12T14:10:46.616356Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","venue":"cs.LG","work_id":"c9cc0378-035d-4db8-9ebc-7007bd5e123e","year":2023},"citing_paper":{"arxiv_id":"2608.10928","last_updated":"2026-08-11T13:58:07Z","snapshot_observed_at":"2026-08-17T15:17:05.825896Z","submitted_at":"2026-08-11T13:58:07Z","title":"ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling","version":1},"reference_index":264,"source":"arxiv_source","source_observed_at":"2026-08-12T14:10:46.230891Z"},"links":{"cited_paper":"/paper/2307.12975","citing_paper":"/paper/2608.10928"},"observation_digest":"sha256:e182f7c2d6758ca2107ac9ea51e3c56a5409f77f3503ebecf94f426155783cef","observation_id":"392f1c28-c7cc-4b29-8c7e-e03f1565dd43","resolution":{"observed_at":"2026-08-12T14:10:46.622427Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2307.12975/citation-record","integrity":"/paper/2307.12975/integrity","json":"/paper/2307.12975/citation-record.json","paper":"/paper/2307.12975"},"outbound":[],"paper":{"arxiv_id":"2307.12975","last_updated":"2023-10-28T21:15:07Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T15:13:41.574673Z","submitted_at":"2023-07-24T17:50:24Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2307.12975."}