{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IHFZODKQQJYE2Z27EINNJ4KXUM","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":"dbd995990b49a402f0ffa513993710bbff46f570d349db22e3c14ca02f001b3d","cross_cats_sorted":["cs.CL","cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T22:12:52Z","title_canon_sha256":"d46dd572ec3f5618ebea3d7f6c29db0491f1792d4005755e0fe5010ab4eb2c28"},"schema_version":"1.0","source":{"id":"2405.19544","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19544","created_at":"2026-07-05T09:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19544v3","created_at":"2026-07-05T09:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19544","created_at":"2026-07-05T09:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"IHFZODKQQJYE","created_at":"2026-07-05T09:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"IHFZODKQQJYE2Z27","created_at":"2026-07-05T09:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"IHFZODKQ","created_at":"2026-07-05T09:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:6e6ae0ec5462eb9724063d3dd3a031b6f4e36d0ad0c680209ec6841b9d83cd2d","target":"graph","created_at":"2026-07-05T09:39:06Z","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/2405.19544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing safety concerns surrounding large language models raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints through Reinforcement Learning from Human Feedback (RLHF). For such constrained RLHF, typical Lagrangian-based primal-dual policy optimization methods are computationally expensive and often unstable. This paper presents a perspective of dualization that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing ","authors_text":"Dongsheng Ding, Edgar Dobriban, Hamed Hassani, Osbert Bastani, Shuo Li, Xinmeng Huang","cross_cats":["cs.CL","cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T22:12:52Z","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19544","kind":"arxiv","version":3},"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":"sha256:8c848cc058cb97aece89221103bf7d046c13fe5e054ba3b9d3554916dc0a68d4","target":"record","created_at":"2026-07-05T09:39:06Z","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":"dbd995990b49a402f0ffa513993710bbff46f570d349db22e3c14ca02f001b3d","cross_cats_sorted":["cs.CL","cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T22:12:52Z","title_canon_sha256":"d46dd572ec3f5618ebea3d7f6c29db0491f1792d4005755e0fe5010ab4eb2c28"},"schema_version":"1.0","source":{"id":"2405.19544","kind":"arxiv","version":3}},"canonical_sha256":"41cb970d5082704d675f221ad4f157a302dc40d48b6e687c6c7bf2816b10746f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41cb970d5082704d675f221ad4f157a302dc40d48b6e687c6c7bf2816b10746f","first_computed_at":"2026-07-05T09:39:06.771131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:06.771131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jc+1E7Itk9X2cN9lKyQsRr6f9KuUxVZ6AMGn7OyZK46umgg7vnMqSRKb0u1ZNpaEMYl+9QVhC0kPkWXaU2LkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:06.771618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19544","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c848cc058cb97aece89221103bf7d046c13fe5e054ba3b9d3554916dc0a68d4","sha256:6e6ae0ec5462eb9724063d3dd3a031b6f4e36d0ad0c680209ec6841b9d83cd2d"],"state_sha256":"9fd149b5f1aaeadd200242805a095c99c07203e2f569d95fe93a19813aa6fc6f"}