{"as_of":"2026-08-07T13:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90facda6663872efac0b072c02248300e543aefd63eab8c1365f186df8558ee4","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T12:59:44.776384Z","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":"2026-08-07T12:59:49.985066Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.06554","last_updated":"2024-10-16T04:48:08Z","snapshot_observed_at":"2026-08-05T02:22:02.033882Z","submitted_at":"2024-10-09T05:17:08Z","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","version":2},"cited_work":{"arxiv_id":"2410.06554","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.06554","snapshot_observed_at":"2026-08-07T12:59:49.985066Z","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","venue":"cs.CL","work_id":"0af7f164-fe8a-4e06-bb3e-ec54a273a35d","year":2024},"citing_paper":{"arxiv_id":"2505.23247","last_updated":"2025-06-17T06:41:40Z","snapshot_observed_at":"2026-08-07T12:47:17.412297Z","submitted_at":"2025-05-29T08:54:06Z","title":"Accelerating RLHF Training with Reward Variance Increase","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:59:44.776384Z"},"links":{"cited_paper":"/paper/2410.06554","citing_paper":"/paper/2505.23247"},"observation_digest":"sha256:a4a3b8ef3170deb74ec024f9f52d973d8c7f1ec8d05b97672e06a44a2f2aaa90","observation_id":"c28f5f59-6cf7-43b9-96d3-637382b39030","resolution":{"observed_at":"2026-08-07T12:59:50.084647Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06554","last_updated":"2024-10-16T04:48:08Z","snapshot_observed_at":"2026-08-05T02:22:02.033882Z","submitted_at":"2024-10-09T05:17:08Z","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06554","snapshot_observed_at":"2026-08-04T20:08:56.202728Z","title":"The accuracy paradox in rlhf: When better reward models don’t yield better language models.arXiv preprint arXiv:2410.06554, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08826","last_updated":"2025-09-10T17:59:31Z","snapshot_observed_at":"2026-08-04T20:08:51.890283Z","submitted_at":"2025-09-10T17:59:31Z","title":"RewardDance: Reward Scaling in Visual Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T20:08:56.202728Z"},"links":{"cited_paper":"/paper/2410.06554","citing_paper":"/paper/2509.08826"},"observation_digest":"sha256:90b08ab65bf96c6bbf498440013073f42594640f7b4e5bf169ba7063d73f2f3d","observation_id":"b272c883-8db7-4937-86eb-367ad3b86f30","resolution":{"observed_at":"2026-08-04T20:08:56.202728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.06554/citation-record","integrity":"/paper/2410.06554/integrity","json":"/paper/2410.06554/citation-record.json","paper":"/paper/2410.06554"},"outbound":[],"paper":{"arxiv_id":"2410.06554","last_updated":"2024-10-16T04:48:08Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T02:22:02.033882Z","submitted_at":"2024-10-09T05:17:08Z","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language 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 2 inbound Pith citation observations for arXiv:2410.06554."}