{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OQ6NAHCKRJLJLGR5AFCMVL654E","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":"b7296cc44e4101e97138faff74689e341bdb157cd35cfb8665876e5a1e9deadf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:54:39Z","title_canon_sha256":"a19a48a8a0e891332b94a730bc46f50180ac01f31c5e42edfd20558979d8d683"},"schema_version":"1.0","source":{"id":"2411.02481","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02481","created_at":"2026-07-05T10:08:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02481v3","created_at":"2026-07-05T10:08:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02481","created_at":"2026-07-05T10:08:24Z"},{"alias_kind":"pith_short_12","alias_value":"OQ6NAHCKRJLJ","created_at":"2026-07-05T10:08:24Z"},{"alias_kind":"pith_short_16","alias_value":"OQ6NAHCKRJLJLGR5","created_at":"2026-07-05T10:08:24Z"},{"alias_kind":"pith_short_8","alias_value":"OQ6NAHCK","created_at":"2026-07-05T10:08:24Z"}],"graph_snapshots":[{"event_id":"sha256:112f5eae9c2cc97dc85f9a2856d70414f033fbf887a9143b051a8eb9fa9790d8","target":"graph","created_at":"2026-07-05T10:08:24Z","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/2411.02481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference tuning relies on high-quality human preference data, which is often expensive and time-consuming to gather. In this paper, we introduce Dr.SoW (Density Ratio of Strong over Weak) a cost-effective method that eliminates the reliance for human annotation by leveraging off-the-shelf LLMs for preference data annotation. Dr.SoW uses the log-density ratio between a better-aligned and a less-aligned LLM as a reward signal. We evaluate Dr.SoW across 221 different LLM pairs and empirically find a strong correlation between the performance gap of the paired models and the quality of the rewar","authors_text":"Akash Srivastava, Guangxuan Xu, Hao Wang, Kai Xu, Shivchander Sudalairaj","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:54:39Z","title":"Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02481","kind":"arxiv","version":3},"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:e22cd93f8bb3f9dd128d21fc35b2cf038b30478330005686188e368895598522","target":"record","created_at":"2026-07-05T10:08:24Z","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":"b7296cc44e4101e97138faff74689e341bdb157cd35cfb8665876e5a1e9deadf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:54:39Z","title_canon_sha256":"a19a48a8a0e891332b94a730bc46f50180ac01f31c5e42edfd20558979d8d683"},"schema_version":"1.0","source":{"id":"2411.02481","kind":"arxiv","version":3}},"canonical_sha256":"743cd01c4a8a56959a3d0144caafdde11b4a773f8545644b99a3cc0010ce19b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"743cd01c4a8a56959a3d0144caafdde11b4a773f8545644b99a3cc0010ce19b7","first_computed_at":"2026-07-05T10:08:24.253043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:24.253043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+PuQ2ZKwOqERVENgTt0fV0GYoORHeWyTwlmlk/hKGPKBdSRSb2XIgSoz2vue36zDeHUJVf/8hFJIwd93VhKSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:24.253490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02481","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e22cd93f8bb3f9dd128d21fc35b2cf038b30478330005686188e368895598522","sha256:112f5eae9c2cc97dc85f9a2856d70414f033fbf887a9143b051a8eb9fa9790d8"],"state_sha256":"6292b5fefc6755e33d08ab0a13200416cbeffa93cac484f61c61eca8aba75cda"}