{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DJDPY7MEZ3LZUNTJBSZVRIB4F7","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":"459612660cdfcc719a58946adedca45dde6b771c2e6a7d38b1dd25513cf5651f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T10:55:38Z","title_canon_sha256":"49354f850619f42eeb8bbed4042883dcaebf2bfae0da26d28f86cadea6917047"},"schema_version":"1.0","source":{"id":"2402.10571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10571","created_at":"2026-07-05T08:28:06Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10571v2","created_at":"2026-07-05T08:28:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10571","created_at":"2026-07-05T08:28:06Z"},{"alias_kind":"pith_short_12","alias_value":"DJDPY7MEZ3LZ","created_at":"2026-07-05T08:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"DJDPY7MEZ3LZUNTJ","created_at":"2026-07-05T08:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"DJDPY7ME","created_at":"2026-07-05T08:28:06Z"}],"graph_snapshots":[{"event_id":"sha256:94cdf5601164b2028ccb599e62e87a2122e93754e9b1ea758651c9741d38ee6b","target":"graph","created_at":"2026-07-05T08:28:06Z","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/2402.10571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated, relies on binary preference data and fine-tunes a language model to increase the likelihood of a preferred response over a dispreferred response. However, not all preference pairs are equal. Sometimes, the preferred response is only slightly better than the dispreferred one. In other cases, the preference is much stronger. For instance, if a response contains ","authors_text":"Afra Amini, Ryan Cotterell, Tim Vieira","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T10:55:38Z","title":"Direct Preference Optimization with an Offset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10571","kind":"arxiv","version":2},"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:b88fa6712460c2e39ae1573196b62437589fecb60a2186c9198f525acf40984d","target":"record","created_at":"2026-07-05T08:28:06Z","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":"459612660cdfcc719a58946adedca45dde6b771c2e6a7d38b1dd25513cf5651f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T10:55:38Z","title_canon_sha256":"49354f850619f42eeb8bbed4042883dcaebf2bfae0da26d28f86cadea6917047"},"schema_version":"1.0","source":{"id":"2402.10571","kind":"arxiv","version":2}},"canonical_sha256":"1a46fc7d84ced79a36690cb358a03c2ff6ced3bd9cdf23e4c9451a8d1169410c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a46fc7d84ced79a36690cb358a03c2ff6ced3bd9cdf23e4c9451a8d1169410c","first_computed_at":"2026-07-05T08:28:06.064828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:06.064828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"890PhpCgjs3ak7wjjKOYISlE5ed9OvmGny4dU/MXVK9INA3DJ2QM5CgJKgtbRdoHeUExrjBN71OwSuEM6ou1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:06.065231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b88fa6712460c2e39ae1573196b62437589fecb60a2186c9198f525acf40984d","sha256:94cdf5601164b2028ccb599e62e87a2122e93754e9b1ea758651c9741d38ee6b"],"state_sha256":"f4c6dabcb1f53e48c2250213ecea5b75ec7d931d11cdb90727373bc388f4c5b8"}