{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GQ4MQ2BACHOIPEC2HVCKPCQ5BI","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":"116fad6b05b402b975636002b6fcb95a252b9dc8f44a95ee175105d17198677d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T07:52:32Z","title_canon_sha256":"c1ea585f4e8a2121f56fe4e2c10aa5df3348c528a0473c300d421b2cc7000af4"},"schema_version":"1.0","source":{"id":"2407.09072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09072","created_at":"2026-07-05T08:43:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09072v1","created_at":"2026-07-05T08:43:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09072","created_at":"2026-07-05T08:43:14Z"},{"alias_kind":"pith_short_12","alias_value":"GQ4MQ2BACHOI","created_at":"2026-07-05T08:43:14Z"},{"alias_kind":"pith_short_16","alias_value":"GQ4MQ2BACHOIPEC2","created_at":"2026-07-05T08:43:14Z"},{"alias_kind":"pith_short_8","alias_value":"GQ4MQ2BA","created_at":"2026-07-05T08:43:14Z"}],"graph_snapshots":[{"event_id":"sha256:f3fc833d4d8fded46cc37dc2c62dbdccd2db83af7e630505b4b02c0ecc37b194","target":"graph","created_at":"2026-07-05T08:43:14Z","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/2407.09072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when implementing these RLHF pipelines, various reparameterization techniques have recently been introduced to sidestep the need for separately learning an RL reward model. Instead, directly fine-tuning for human preferences is achieved via the minimization of a single closed-form training objective, a process originally referred to as direct preference optimization (DPO) ","authors_text":"David Wipf, Tong He, Xiangkun Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T07:52:32Z","title":"New Desiderata for Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09072","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":"sha256:31e79fb93e53199cb1272f9f7b9638e47bf531f451824e8ef3b3e5216b339378","target":"record","created_at":"2026-07-05T08:43:14Z","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":"116fad6b05b402b975636002b6fcb95a252b9dc8f44a95ee175105d17198677d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T07:52:32Z","title_canon_sha256":"c1ea585f4e8a2121f56fe4e2c10aa5df3348c528a0473c300d421b2cc7000af4"},"schema_version":"1.0","source":{"id":"2407.09072","kind":"arxiv","version":1}},"canonical_sha256":"3438c8682011dc87905a3d44a78a1d0a1ea338a8ae4c62c2f9daa93d99198738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3438c8682011dc87905a3d44a78a1d0a1ea338a8ae4c62c2f9daa93d99198738","first_computed_at":"2026-07-05T08:43:14.223890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:14.223890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oBXmBhCHdkVrOg1gT5DXSDVPrP13R4ZvC+nDM8b2HOHpPSKHOghGDQeAWVfmSamd3ETzS2pYw11XPt5OxUJiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:14.224396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31e79fb93e53199cb1272f9f7b9638e47bf531f451824e8ef3b3e5216b339378","sha256:f3fc833d4d8fded46cc37dc2c62dbdccd2db83af7e630505b4b02c0ecc37b194"],"state_sha256":"22c25d356a05ea8c1044f774340d6c224d9cd5bb2136c63dec44d09ef53bf85c"}