{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O64Z5DXFCCYDTL6RLSU3YRJ4RZ","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":"4742bb624bb30ffac47b6b4e06ca003eb230615cd0d6baa30665c020c99f4e88","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:38:17Z","title_canon_sha256":"133a594afe60225e8a07f2b91e48d218d330ccf816a2155f6375582126dc4fdd"},"schema_version":"1.0","source":{"id":"2507.07855","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07855","created_at":"2026-06-23T03:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07855v4","created_at":"2026-06-23T03:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07855","created_at":"2026-06-23T03:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"O64Z5DXFCCYD","created_at":"2026-06-23T03:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"O64Z5DXFCCYDTL6R","created_at":"2026-06-23T03:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"O64Z5DXF","created_at":"2026-06-23T03:13:46Z"}],"graph_snapshots":[{"event_id":"sha256:078ce428773fed02dcacbee62513824e05a539fc50f20a3f2f7a3a97b2a6a1aa","target":"graph","created_at":"2026-06-23T03:13:46Z","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/2507.07855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Normative theories allow one to elicit key parts of a ML algorithm from first principles, which is crucial at a time of championed scrutiny for ML work. Direct Preference Optimization (DPO) cleverly bypasses reward modeling by making an explicit link with a specific normative model of human choice. Our paper elevates this connection to the full generality of DPO's normative framework. Getting there requires reworking human choice theory's textbook path for a better RLHF/ML fit. It elevates the connection to a remarkably broad viewpoint on preference optimization, considering the current panora","authors_text":"Andrew Hard, Brice Magdalou, Ehsan Amid, John Lambert, Richard Nock, Shujian Zhang, Wenxuan Zhou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:38:17Z","title":"DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07855","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:fb9e577f39d522bed43ae5d3165e70c7defd11f4e2c1d55a27bd2434e4049bc9","target":"record","created_at":"2026-06-23T03:13:46Z","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":"4742bb624bb30ffac47b6b4e06ca003eb230615cd0d6baa30665c020c99f4e88","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:38:17Z","title_canon_sha256":"133a594afe60225e8a07f2b91e48d218d330ccf816a2155f6375582126dc4fdd"},"schema_version":"1.0","source":{"id":"2507.07855","kind":"arxiv","version":4}},"canonical_sha256":"77b99e8ee510b039afd15ca9bc453c8e59cafa6cd657f5368468f8a364061d0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77b99e8ee510b039afd15ca9bc453c8e59cafa6cd657f5368468f8a364061d0c","first_computed_at":"2026-06-23T03:13:46.184638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:46.184638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDlTxL3B8S8dx2NgD4zsk/njBJsF1xlHy9mz7u/SD1HjVAZe138RRX8YYtMwv7E5aBl73yKc47cqwj7q2cskAw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:46.185258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07855","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb9e577f39d522bed43ae5d3165e70c7defd11f4e2c1d55a27bd2434e4049bc9","sha256:078ce428773fed02dcacbee62513824e05a539fc50f20a3f2f7a3a97b2a6a1aa"],"state_sha256":"b729e3c0f69aa41f090ff8be8fb7ac98da8e403dd5695d9ec31c6d27262ce0ca"}