{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5NNTALUTGGHLM3QFZLLAZPY6HZ","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":"612dc8f92a54d99f74197f617859d18320ea49f5b8997dfa1a6c47dfa6f3bbda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T08:35:48Z","title_canon_sha256":"665ff312c9e08987a0e91d923c89d071bebdccc763c37000ac9708e608e0cde1"},"schema_version":"1.0","source":{"id":"2405.17956","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17956","created_at":"2026-07-05T11:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17956v4","created_at":"2026-07-05T11:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17956","created_at":"2026-07-05T11:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"5NNTALUTGGHL","created_at":"2026-07-05T11:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"5NNTALUTGGHLM3QF","created_at":"2026-07-05T11:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"5NNTALUT","created_at":"2026-07-05T11:08:57Z"}],"graph_snapshots":[{"event_id":"sha256:628ecf2a0019760e1a092a20c07b251c0b532a10ffeb891715c5fc0df5e33fdc","target":"graph","created_at":"2026-07-05T11:08:57Z","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/2405.17956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood estimation, it compromises on the ability to easily tune language models to maximize auxiliary, non-preferential objectives according to the LLM designer's preferences (e.g., tuning lexical style or minimizing specific kinds of harmful content). Critically, these designer objectives may not be amply human-labeled or represented in available data, align with use","authors_text":"Anirudhan Badrinath, Jiajing Xu, Prabhat Agarwal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T08:35:48Z","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17956","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":"sha256:31900e76a666e7f94b739dc66acac6e6fbcf08bda89a0f432ea0bc3744db5688","target":"record","created_at":"2026-07-05T11:08:57Z","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":"612dc8f92a54d99f74197f617859d18320ea49f5b8997dfa1a6c47dfa6f3bbda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T08:35:48Z","title_canon_sha256":"665ff312c9e08987a0e91d923c89d071bebdccc763c37000ac9708e608e0cde1"},"schema_version":"1.0","source":{"id":"2405.17956","kind":"arxiv","version":4}},"canonical_sha256":"eb5b302e93318eb66e05cad60cbf1e3e5ad8debb96df7dbea80ed9fe64fbde5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb5b302e93318eb66e05cad60cbf1e3e5ad8debb96df7dbea80ed9fe64fbde5d","first_computed_at":"2026-07-05T11:08:57.710885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:57.710885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FNB7INdwi/THQwdZDSFHmR98PGE5WDDOEGueYH16QN4vNqsKBLcsxYo1/Cdnrnx9aKmX57XfcSGD1q4mJro6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:57.711365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17956","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31900e76a666e7f94b739dc66acac6e6fbcf08bda89a0f432ea0bc3744db5688","sha256:628ecf2a0019760e1a092a20c07b251c0b532a10ffeb891715c5fc0df5e33fdc"],"state_sha256":"3600b7120ef9ef02f06e61acef3a2d0d844a91a96be1e7866ec80beaa8047b58"}