{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4UOHAOSX5FZ6C7HQGEFABGPXYE","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":"dc140aab1452e1f759861c55dcb53db270263e6fd1436c04097620cf1627ec39","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T00:52:03Z","title_canon_sha256":"4eba20eca6d44e2a2df8be09acf4632b68b2e6c3ca89693603506f4f1d7a1be5"},"schema_version":"1.0","source":{"id":"2410.05584","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05584","created_at":"2026-07-05T10:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05584v5","created_at":"2026-07-05T10:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05584","created_at":"2026-07-05T10:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"4UOHAOSX5FZ6","created_at":"2026-07-05T10:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"4UOHAOSX5FZ6C7HQ","created_at":"2026-07-05T10:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"4UOHAOSX","created_at":"2026-07-05T10:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:2f1d5c63b83df03471c8a04b473fd5aff86ffe5730bcffbb1af20ce0c1dcd0e0","target":"graph","created_at":"2026-07-05T10:14:06Z","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/2410.05584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is straightforward and widely adopted, the relationship between RM accuracy and downstream policy performance remains under-explored. In this work, we conduct experiments in a synthetic setting to investigate how differences in RM measured by accuracy translate into gaps in optimized policy performance. Our findings reveal that while there is a weak positive correl","authors_text":"Ben He, Debing Zhang, Hongyu Lin, Jie Lou, Le Sun, Xianpei Han, Xing Yu, Xinyu Lu, Xueru Wen, Yaojie Lu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T00:52:03Z","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05584","kind":"arxiv","version":5},"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":"sha256:27e87c84a66a8c7814d1d6635e461e4a8aecdd579d6f3269478c4efa78a862ce","target":"record","created_at":"2026-07-05T10:14:06Z","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":"dc140aab1452e1f759861c55dcb53db270263e6fd1436c04097620cf1627ec39","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T00:52:03Z","title_canon_sha256":"4eba20eca6d44e2a2df8be09acf4632b68b2e6c3ca89693603506f4f1d7a1be5"},"schema_version":"1.0","source":{"id":"2410.05584","kind":"arxiv","version":5}},"canonical_sha256":"e51c703a57e973e17cf0310a0099f7c12d7144532527c649040005ba927cdca4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e51c703a57e973e17cf0310a0099f7c12d7144532527c649040005ba927cdca4","first_computed_at":"2026-07-05T10:14:06.121143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:06.121143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H7Lfsw6RIDNuVOJ1fMDYFpNMVlmc40FxYwtrjMOThi0VUL3jlAvurC4hmJC9pxgkQTHAAHvCbDJnu9XUMpKyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:06.121645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05584","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27e87c84a66a8c7814d1d6635e461e4a8aecdd579d6f3269478c4efa78a862ce","sha256:2f1d5c63b83df03471c8a04b473fd5aff86ffe5730bcffbb1af20ce0c1dcd0e0"],"state_sha256":"a7526232d4d04b96362edfb8e5b0fffbab46f141d41838f736810f6abd3f405c"}