{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B4XZW4C5IK2TC4DXQAWUJYJ5AN","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":"a57fb6347fa87e9e667512c798c19581021aecffe8cb4728de255dce9cde04fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T10:39:34Z","title_canon_sha256":"bdf640b694b799bed6d53c98eaecd0f31cba01d60c7170a5c0adbfbd12476987"},"schema_version":"1.0","source":{"id":"2410.22891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22891","created_at":"2026-07-05T09:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22891v1","created_at":"2026-07-05T09:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22891","created_at":"2026-07-05T09:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"B4XZW4C5IK2T","created_at":"2026-07-05T09:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"B4XZW4C5IK2TC4DX","created_at":"2026-07-05T09:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"B4XZW4C5","created_at":"2026-07-05T09:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:2bec3cb62712a4c87a3a9e5773661d746d917888b0e5c2ac9ce8ab8e8d26d3bc","target":"graph","created_at":"2026-07-05T09:28:37Z","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/2410.22891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference dataset, DPO enhances generation quality by increasing the likelihood of producing preferred sentences over less favored ones. Preference datasets are typically created by selecting preferred sentences through a voting process involving multiple individuals, as opinions can vary due to the subjective nature of human preferences. While the number of votes offer","authors_text":"Byung-Jun Lee, Jae Hyeon Cho, Minkyung Park","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T10:39:34Z","title":"VPO: Leveraging the Number of Votes in Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22891","kind":"arxiv","version":1},"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":"sha256:725c20981958b4ce2a8e6a0c15bbaa0d759a5edfd92e3e00cd28b1ce0cde235b","target":"record","created_at":"2026-07-05T09:28:37Z","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":"a57fb6347fa87e9e667512c798c19581021aecffe8cb4728de255dce9cde04fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T10:39:34Z","title_canon_sha256":"bdf640b694b799bed6d53c98eaecd0f31cba01d60c7170a5c0adbfbd12476987"},"schema_version":"1.0","source":{"id":"2410.22891","kind":"arxiv","version":1}},"canonical_sha256":"0f2f9b705d42b5317077802d44e13d036b1ee9f95b1deb81d450c67353118140","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f2f9b705d42b5317077802d44e13d036b1ee9f95b1deb81d450c67353118140","first_computed_at":"2026-07-05T09:28:37.605476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:37.605476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGIChaxjdUUuKd4Xb2ejwwnxKYF/KkvQF+DKDF+0MMEBUvbd/LNmGZGeYnlQvcZVQebHDkpZkVd+r3KTPOXhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:37.605927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:725c20981958b4ce2a8e6a0c15bbaa0d759a5edfd92e3e00cd28b1ce0cde235b","sha256:2bec3cb62712a4c87a3a9e5773661d746d917888b0e5c2ac9ce8ab8e8d26d3bc"],"state_sha256":"b68ac89ce671ab8140c4e3b8d2f53c211c35b7df84168f01ac1090e851faa2d2"}