{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R2BKH6I3FCDMF7JRKP3NVZASUS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"46e2c65b6bc40a315bc38efe38b5b946ed728cc57d3209aeed438f319a9a1e5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:08Z","title_canon_sha256":"e4b524ed13c7acaffa7cc0522dceea9ea3da6c578fa85f8ab64db2af390e48c3"},"schema_version":"1.0","source":{"id":"2410.06554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06554","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06554v2","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06554","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"R2BKH6I3FCDM","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"R2BKH6I3FCDMF7JR","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"R2BKH6I3","created_at":"2026-07-05T09:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:a4ff0b8917d4932590a8d7aab6ad4b361a265e8998b5bde0c0d83b8a786a9ec3","target":"graph","created_at":"2026-07-05T09:21:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.06554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training. This study explores whether stronger reward models invariably lead to better language models. In this paper, through experiments on relevance, factuality, and completeness tasks using the QA-FEEDBACK dataset and reward models based on Longformer, we uncover a surprising paradox: language models trained with moderately accurate reward models outperform those gu","authors_text":"Dawei Zhu, Wei Zhang, Xiaoyu Shen, Xinghao Chen, Yanjun Chen, Yirong Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:08Z","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06554","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:631169eb377125f39710e5a786a6d8e78ef8e8434553860d20e0a0317463dbb5","target":"record","created_at":"2026-07-05T09:21:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"46e2c65b6bc40a315bc38efe38b5b946ed728cc57d3209aeed438f319a9a1e5d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:08Z","title_canon_sha256":"e4b524ed13c7acaffa7cc0522dceea9ea3da6c578fa85f8ab64db2af390e48c3"},"schema_version":"1.0","source":{"id":"2410.06554","kind":"arxiv","version":2}},"canonical_sha256":"8e82a3f91b2886c2fd3153f6dae412a4ab75f7f8f1bdc8316a3cedbce748d84c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e82a3f91b2886c2fd3153f6dae412a4ab75f7f8f1bdc8316a3cedbce748d84c","first_computed_at":"2026-07-05T09:21:08.021137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:08.021137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pr1CcAiflR5fbsNI1kSDM7EEbByiHYwxBr9nbw3xBBVbvY/8BEzLi9iu6OH+ggYQZ1hZP6XsS9Cfu/c1GESoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:08.021640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:631169eb377125f39710e5a786a6d8e78ef8e8434553860d20e0a0317463dbb5","sha256:a4ff0b8917d4932590a8d7aab6ad4b361a265e8998b5bde0c0d83b8a786a9ec3"],"state_sha256":"9a8ca4776ad829bb001659070a50904c10485e753f2f673bc72d258b51f20041"}