{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7Z25GMP54JO2FTN572J65TCQ6B","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":"fbce2515b82d4fff42ed861de2034508e1cd59dcf8897a3e22d99e770a7162e8","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T14:19:23Z","title_canon_sha256":"3b80831e9e2aa4939a6d652b2cb25d5b7131ec5b33eb30e670b774d57c3ef93d"},"schema_version":"1.0","source":{"id":"2505.12435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12435","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12435v1","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12435","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"7Z25GMP54JO2","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"7Z25GMP54JO2FTN5","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"7Z25GMP5","created_at":"2026-07-05T11:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:615ec0a8836d04dfbfa9cd9ac457df777eb6490006e3d4403d24a2f836d4990c","target":"graph","created_at":"2026-07-05T11:05:04Z","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/2505.12435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate human-preferred response is limited and the results of DPO are far from resilient. To address these limitations, in this paper we propose a novel Self-Guided Direct Preference Optimization algorithm, i.e., SGDPO, which incorporates a pilot term to steer the gradient flow during the optimization process, allowing for fine-grained control over the updates of chosen an","authors_text":"Ji Liu, Jun Wu, Lulu Wang, Wenqiao Zhu, Yulun Zhang","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T14:19:23Z","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12435","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":"sha256:12386e4cfe7f12fe63b62d9eefb0d769b349d024af3f3b877a60e96520eade42","target":"record","created_at":"2026-07-05T11:05:04Z","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":"fbce2515b82d4fff42ed861de2034508e1cd59dcf8897a3e22d99e770a7162e8","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T14:19:23Z","title_canon_sha256":"3b80831e9e2aa4939a6d652b2cb25d5b7131ec5b33eb30e670b774d57c3ef93d"},"schema_version":"1.0","source":{"id":"2505.12435","kind":"arxiv","version":1}},"canonical_sha256":"fe75d331fde25da2cdbdfe93eecc50f046c0c3cab3dd8be9c9747a4fb31def75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe75d331fde25da2cdbdfe93eecc50f046c0c3cab3dd8be9c9747a4fb31def75","first_computed_at":"2026-07-05T11:05:04.175710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:04.175710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+9EAhNGB0WgcNlUQSeP7/Wa2aHRhDGC8kMsaCvnFccSyQXwAwOOmP/xsSQROmiKI13cmBaO1/Ae08gqgOaGwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:04.176131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12386e4cfe7f12fe63b62d9eefb0d769b349d024af3f3b877a60e96520eade42","sha256:615ec0a8836d04dfbfa9cd9ac457df777eb6490006e3d4403d24a2f836d4990c"],"state_sha256":"f1d7c3118e551d83dd81aecf0f012ca842910c3368d054dd832012912de0c0fa"}