{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RQ4AQ6KGRT4TBOY3HURYNLFMP6","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":"6f0855a0f907c265fb2c596a60915e060084211015d1487f643d7b643b28e714","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T02:11:45Z","title_canon_sha256":"f03d4edda1cbddb55b3e41b15544148895cedc74278896c63a24b02b8461dd0b"},"schema_version":"1.0","source":{"id":"2410.21662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21662","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21662v2","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21662","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"RQ4AQ6KGRT4T","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"RQ4AQ6KGRT4TBOY3","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"RQ4AQ6KG","created_at":"2026-07-05T10:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:c926615c4ee44641612b88bb577ddbc62ae532af3e4a8f50a4c9959aeadd145d","target":"graph","created_at":"2026-07-05T10:14:47Z","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/2410.21662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that generalizes and extends existing approaches. $f$-PO minimizes $f$-divergences between the optimized policy and the optimal policy, encompassing a broad family of alignment methods using various divergences. Our approach unifies previous algorithms like DPO and EXO, while offering new variants through different choices of $f$-divergences. We provide theoretica","authors_text":"Jiaqi Han, Mingjian Jiang, Minkai Xu, Stefano Ermon, Yuxuan Song","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T02:11:45Z","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21662","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:d05e549132b37fe5fcc70f586697c39f564305c410e0a36897954a9532499fd0","target":"record","created_at":"2026-07-05T10:14:47Z","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":"6f0855a0f907c265fb2c596a60915e060084211015d1487f643d7b643b28e714","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T02:11:45Z","title_canon_sha256":"f03d4edda1cbddb55b3e41b15544148895cedc74278896c63a24b02b8461dd0b"},"schema_version":"1.0","source":{"id":"2410.21662","kind":"arxiv","version":2}},"canonical_sha256":"8c380879468cf930bb1b3d2386acac7faf37e97ba9b8a8bc55123e59243448eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c380879468cf930bb1b3d2386acac7faf37e97ba9b8a8bc55123e59243448eb","first_computed_at":"2026-07-05T10:14:47.359192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:47.359192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Im/B7AfclyKNXat8zoS5q/+p+bBwfuTMFQJKwhN/M9shVzCRu1F9eqLLaHDTP5Yw2gnKxfpGDivUF4cAxyyIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:47.359858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d05e549132b37fe5fcc70f586697c39f564305c410e0a36897954a9532499fd0","sha256:c926615c4ee44641612b88bb577ddbc62ae532af3e4a8f50a4c9959aeadd145d"],"state_sha256":"714c43d337b05e7b5cb6dae3833d1a38c27b5407a2174d9718e9291d90e71bff"}