{"as_of":"2026-08-07T22:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0fc597f91b80fdcc7fa44f99d6ae8c04c4df74a303b597e300ca9caf827ae11","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T22:56:33.472641Z","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":"2026-08-05T13:20:39.606465Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.12086","last_updated":"2024-10-25T12:04:26Z","snapshot_observed_at":"2026-07-06T17:18:52.483885Z","submitted_at":"2024-01-22T16:24:43Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12086","snapshot_observed_at":"2026-08-06T22:56:33.472641Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20274","last_updated":"2025-06-25T09:34:25Z","snapshot_observed_at":"2026-08-07T12:25:51.783364Z","submitted_at":"2025-06-25T09:34:25Z","title":"Enterprise Large Language Model Evaluation Benchmark","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:56:33.472641Z"},"links":{"cited_paper":"/paper/2401.12086","citing_paper":"/paper/2506.20274"},"observation_digest":"sha256:8a21ba6efbda233340d727a72d47d946506974f796b5585b978584e2c99888bf","observation_id":"139a865c-3c99-47d3-bdc5-87120610f228","resolution":{"observed_at":"2026-08-06T22:56:33.472641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12086","last_updated":"2024-10-25T12:04:26Z","snapshot_observed_at":"2026-07-06T17:18:52.483885Z","submitted_at":"2024-01-22T16:24:43Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12086","snapshot_observed_at":"2026-08-06T22:28:07.646010Z","title":"West-of-n: Synthetic preference generation for improved reward modeling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.21495","last_updated":"2025-06-26T17:25:49Z","snapshot_observed_at":"2026-08-06T22:21:21.361920Z","submitted_at":"2025-06-26T17:25:49Z","title":"Bridging Offline and Online Reinforcement Learning for LLMs","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T22:28:07.646010Z"},"links":{"cited_paper":"/paper/2401.12086","citing_paper":"/paper/2506.21495"},"observation_digest":"sha256:fef9a8b91949ec9e878bc3456b2a1f3d721a975efb90d71bae08d5d6fdec439d","observation_id":"d924b7eb-7f25-42fe-836d-3b7a7fe23925","resolution":{"observed_at":"2026-08-06T22:28:07.646010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12086","last_updated":"2024-10-25T12:04:26Z","snapshot_observed_at":"2026-07-06T17:18:52.483885Z","submitted_at":"2024-01-22T16:24:43Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","version":2},"cited_work":{"arxiv_id":"2401.12086","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.12086","snapshot_observed_at":"2026-08-05T13:20:39.606465Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","venue":"cs.CL","work_id":"f32f7260-51f5-4803-bb62-1c69dfb9ce30","year":2024},"citing_paper":{"arxiv_id":"2509.00728","last_updated":"2025-08-31T07:45:40Z","snapshot_observed_at":"2026-08-07T09:28:21.792586Z","submitted_at":"2025-08-31T07:45:40Z","title":"A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives","version":1},"reference_index":115,"source":"pdf_text","source_observed_at":"2026-08-05T13:20:39.171623Z"},"links":{"cited_paper":"/paper/2401.12086","citing_paper":"/paper/2509.00728"},"observation_digest":"sha256:b607f3e16422d9fad8dbbff4c8305495da0d952b16ae24b093d28dc93e8d8e9b","observation_id":"b5cc09f4-cc04-4bc2-9819-1bbb87653000","resolution":{"observed_at":"2026-08-05T13:20:39.610566Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.12086/citation-record","integrity":"/paper/2401.12086/integrity","json":"/paper/2401.12086/citation-record.json","paper":"/paper/2401.12086"},"outbound":[],"paper":{"arxiv_id":"2401.12086","last_updated":"2024-10-25T12:04:26Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:18:52.483885Z","submitted_at":"2024-01-22T16:24:43Z","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.12086."}