{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6W27QQ74BXA3IGPGQZP2AQP2VH","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":"662d6d8435d867adabe7680272fc7a9fbbd03e9f49463ce0dacae128cdf7bba6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T09:09:16Z","title_canon_sha256":"d8e367c2134925e9e14298bbe6050f071f6851781aae08fb4a50868ae1f1cc39"},"schema_version":"1.0","source":{"id":"2409.14836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14836","created_at":"2026-07-05T11:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14836v3","created_at":"2026-07-05T11:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14836","created_at":"2026-07-05T11:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"6W27QQ74BXA3","created_at":"2026-07-05T11:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"6W27QQ74BXA3IGPG","created_at":"2026-07-05T11:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"6W27QQ74","created_at":"2026-07-05T11:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:87f0c627e7d650d4932425afa26964a53e62719ccaa3c157897be12489306a0e","target":"graph","created_at":"2026-07-05T11:58:20Z","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/2409.14836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have endeavored to alleviate this issue by modifying the objective function, they achieved that at the cost of alignment performance degradation. In this paper, we innovatively incorporate regularization from the perspective of weight updating to curb alignment overfitting. Through the pilot experiment, we discovered that there exists a positive correlation between overfi","authors_text":"Chao Pang, Chenxu Yang, Hua Wu, Naibin Gu, Ruipeng Jia, Siyuan Chen, Weichong Yin, Weiping Wang, Yu Sun, Zheng Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T09:09:16Z","title":"Orthogonal Finetuning for Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14836","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":"sha256:0b55c85279aaf2be769e4bb345ca089dc103985b454faf14a60f65cffeec00f4","target":"record","created_at":"2026-07-05T11:58:20Z","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":"662d6d8435d867adabe7680272fc7a9fbbd03e9f49463ce0dacae128cdf7bba6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T09:09:16Z","title_canon_sha256":"d8e367c2134925e9e14298bbe6050f071f6851781aae08fb4a50868ae1f1cc39"},"schema_version":"1.0","source":{"id":"2409.14836","kind":"arxiv","version":3}},"canonical_sha256":"f5b5f843fc0dc1b419e6865fa041faa9dca35b2da8c6ebdb2cb8dc947989b0fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b5f843fc0dc1b419e6865fa041faa9dca35b2da8c6ebdb2cb8dc947989b0fe","first_computed_at":"2026-07-05T11:58:20.742741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:20.742741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Thp565wcBDLNVD+uu036v9Jyy/lxVlKMkxCmYNfL4W0kpvpNxJC6fubcYD04ovzg2nuPjepTdLH1ubS9mtkiAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:20.743190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b55c85279aaf2be769e4bb345ca089dc103985b454faf14a60f65cffeec00f4","sha256:87f0c627e7d650d4932425afa26964a53e62719ccaa3c157897be12489306a0e"],"state_sha256":"d5189b519752c37888a745ab568e5f8c3069489bf99e890b4ebb57c053a192d0"}