{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P7L6C64U334UV63NASGA2R462N","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":"37e0f6efd8b321c7e4b1b79181dbbfb52525bc8f8270a88947b56aa443f8da51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-11T21:41:27Z","title_canon_sha256":"1cc4dbcbcde760120290a5502dc8495841959fa756df9c3163fcba42e5f07c76"},"schema_version":"1.0","source":{"id":"2501.06645","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06645","created_at":"2026-07-05T11:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06645v3","created_at":"2026-07-05T11:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06645","created_at":"2026-07-05T11:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"P7L6C64U334U","created_at":"2026-07-05T11:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"P7L6C64U334UV63N","created_at":"2026-07-05T11:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"P7L6C64U","created_at":"2026-07-05T11:44:00Z"}],"graph_snapshots":[{"event_id":"sha256:519cd640f01db81435c2b18f539a130885cb72b1a715c578d1763287f0bfc4c5","target":"graph","created_at":"2026-07-05T11:44:00Z","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/2501.06645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward model, and focus on training it to correct misranked preference pairs. However, recent work~\\citep{chen2024preference} empirically finds that DPO training \\textit{rarely improves these misranked preference pairs}, despite its gradient emphasizing on these cases. We introduce FocalPO, a DPO variant that instead \\textit{down-weighs} misranked preference pairs ","authors_text":"Jindong Gu, Tong Liu, Volker Tresp, Wenxuan Zhou, Xiao Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-11T21:41:27Z","title":"FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06645","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":"sha256:8369e709988f8f9f425c04f9056f58ec3cc3db107921d38cc6d4293828c6e23b","target":"record","created_at":"2026-07-05T11:44:00Z","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":"37e0f6efd8b321c7e4b1b79181dbbfb52525bc8f8270a88947b56aa443f8da51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-11T21:41:27Z","title_canon_sha256":"1cc4dbcbcde760120290a5502dc8495841959fa756df9c3163fcba42e5f07c76"},"schema_version":"1.0","source":{"id":"2501.06645","kind":"arxiv","version":3}},"canonical_sha256":"7fd7e17b94def94afb6d048c0d479ed342c3bc3b5ab72417ec9c41663ce6503f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd7e17b94def94afb6d048c0d479ed342c3bc3b5ab72417ec9c41663ce6503f","first_computed_at":"2026-07-05T11:44:00.418282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:00.418282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ywvwazY+YqvevnEUPB9foDFpBPSw243GtNs1JeUVR8rrGx9Gbwevo6E9mrBimDq1pXa7k2PkXMnJORfn362rAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:00.418769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06645","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8369e709988f8f9f425c04f9056f58ec3cc3db107921d38cc6d4293828c6e23b","sha256:519cd640f01db81435c2b18f539a130885cb72b1a715c578d1763287f0bfc4c5"],"state_sha256":"b9b99eea6b0ab96600b591fd418d916988cf9877aa6a756d335d85e08c768fc8"}