{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AFWDOC6W4HNPTBNQD7CONVWA3I","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":"a201e27d063a3ce3b978ad56e1073108a5bf5e4c42c5a88f4aa1c24c291b6ed7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T14:24:30Z","title_canon_sha256":"f22aff06401921b42d2018b5cc669876092160669594a58971b01c2996595207"},"schema_version":"1.0","source":{"id":"2406.10957","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10957","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10957v4","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10957","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_12","alias_value":"AFWDOC6W4HNP","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_16","alias_value":"AFWDOC6W4HNPTBNQ","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_8","alias_value":"AFWDOC6W","created_at":"2026-07-05T09:45:50Z"}],"graph_snapshots":[{"event_id":"sha256:fc9717e0b3f1961f0275ccf5e96f956f13cf2d7a2a84cf3eee6c670ac75abb68","target":"graph","created_at":"2026-07-05T09:45:50Z","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/2406.10957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF). Despite its promising efficacy, DPO faces a notable drawback: \"verbosity\", a common over-optimization phenomenon also observed in RLHF. While previous studies mainly attributed verbosity to biased labels within the data, we propose that the issue also stems from an inherent algorithmic length reliance in DPO. Specifically,","authors_text":"Di Yin, Jiazheng Li, Junru Lu, Meng Zhao, Siyu An, Xing Sun, Yulan He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T14:24:30Z","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10957","kind":"arxiv","version":4},"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":"sha256:0ae8dee13c89a3e23b845fbea43a0c17bac6b1e54a0d11a2fe8d10fe24f3a271","target":"record","created_at":"2026-07-05T09:45:50Z","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":"a201e27d063a3ce3b978ad56e1073108a5bf5e4c42c5a88f4aa1c24c291b6ed7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T14:24:30Z","title_canon_sha256":"f22aff06401921b42d2018b5cc669876092160669594a58971b01c2996595207"},"schema_version":"1.0","source":{"id":"2406.10957","kind":"arxiv","version":4}},"canonical_sha256":"016c370bd6e1daf985b01fc4e6d6c0da0c5b5740125be02bf863678dd49ec770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"016c370bd6e1daf985b01fc4e6d6c0da0c5b5740125be02bf863678dd49ec770","first_computed_at":"2026-07-05T09:45:50.404544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:50.404544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dl+OvHoUQ/s+tTJ6vg0aon9FnQ3ptmQMHoJ0FJcPRAGbs0sh7jPUIagQgT6b8ltobu1bI7A7cUIFGoM9wk64Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:50.404997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10957","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ae8dee13c89a3e23b845fbea43a0c17bac6b1e54a0d11a2fe8d10fe24f3a271","sha256:fc9717e0b3f1961f0275ccf5e96f956f13cf2d7a2a84cf3eee6c670ac75abb68"],"state_sha256":"742dd1a16de864933e52761d04fd1d018f35e903cc2aeaa93ccaf7ce4a9e5e87"}