{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJ2WXQJX44UDFPYCYQJ3UHZF2F","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":"c24ba1a6f383579f9db2b5e506906db2c8dba2964f7ab95ab586ffe4e1cab8a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:45:15Z","title_canon_sha256":"9200ecaf1f762d55301725b9701cf3040f99a22f5b409bf1aff571302d5938ec"},"schema_version":"1.0","source":{"id":"2503.11701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11701","created_at":"2026-07-05T10:31:58Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11701v1","created_at":"2026-07-05T10:31:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11701","created_at":"2026-07-05T10:31:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZJ2WXQJX44UD","created_at":"2026-07-05T10:31:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZJ2WXQJX44UDFPYC","created_at":"2026-07-05T10:31:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZJ2WXQJX","created_at":"2026-07-05T10:31:58Z"}],"graph_snapshots":[{"event_id":"sha256:c3164f5a5f284fff396dc7a86ebb875387e551054f73b82bb10b9cbd0ddf8d5e","target":"graph","created_at":"2026-07-05T10:31:58Z","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/2503.11701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated unprecedented generative capabilities, yet their alignment with human values remains critical for ensuring helpful and harmless deployments. While Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful paradigm for aligning LLMs with human preferences, its reliance on complex reward modeling introduces inherent trade-offs in computational efficiency and training stability. In this context, Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative that directly optimizes LLMs using human p","authors_text":"Dacheng Tao, Fei Huang, Junjie Zhang, Kongcheng Zhang, Mingli Song, Rongcheng Tu, Shunyu Liu, Ting-En Lin, Wenkai Fang, Yang Zhou, Yongbin Li, Zetian Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:45:15Z","title":"A Survey of Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11701","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:f9108726e3fcd5558ecefcb0db39188489aa32fbac684bff8c917e93e9c5da94","target":"record","created_at":"2026-07-05T10:31:58Z","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":"c24ba1a6f383579f9db2b5e506906db2c8dba2964f7ab95ab586ffe4e1cab8a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T08:45:15Z","title_canon_sha256":"9200ecaf1f762d55301725b9701cf3040f99a22f5b409bf1aff571302d5938ec"},"schema_version":"1.0","source":{"id":"2503.11701","kind":"arxiv","version":1}},"canonical_sha256":"ca756bc137e72832bf02c413ba1f25d15826576897240576d27a02338264901c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca756bc137e72832bf02c413ba1f25d15826576897240576d27a02338264901c","first_computed_at":"2026-07-05T10:31:58.404308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:58.404308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a2mpzx40Pk1dW74hfE4IYlf06l1g+LTX1feQVn5dMM9ZXy/fRTvfmSOc0AwGKqXdGC3ky2OwBbjEAInTHSYXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:58.404856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9108726e3fcd5558ecefcb0db39188489aa32fbac684bff8c917e93e9c5da94","sha256:c3164f5a5f284fff396dc7a86ebb875387e551054f73b82bb10b9cbd0ddf8d5e"],"state_sha256":"65661ab5acfea795ae84245268f4e1d242329ac176cd59fca231f258b3973485"}