{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HFSUFVQXRS24JHXNHQPXKTDWRN","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":"9fc854972dd4426d88776975c6cd4fd9bcd1ad93f9a437b4a37d7b862db726b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T05:58:26Z","title_canon_sha256":"cc1905f928e4d4bb331fb771ffcb6819d96a47c161bc473d41d6229e77786cf9"},"schema_version":"1.0","source":{"id":"2505.10892","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10892","created_at":"2026-06-08T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10892v2","created_at":"2026-06-08T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10892","created_at":"2026-06-08T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"HFSUFVQXRS24","created_at":"2026-06-08T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"HFSUFVQXRS24JHXN","created_at":"2026-06-08T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"HFSUFVQX","created_at":"2026-06-08T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:d93c7ad14957f170aec6fbb04430f288d771e12293f6c609854f13755a8848fd","target":"graph","created_at":"2026-06-08T01:03:44Z","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/2505.10892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training LLMs with RLHF and preference optimization methods (e.g., DPO, IPO) has greatly improved alignment, yet these approaches assume a single objective. In reality, humans express multiple, often conflicting objectives, such as helpfulness and harmlessness, with no natural scalarization. We study the multi-objective preference alignment problem, where a policy must balance several objectives simultaneously. We propose Multi-Objective Preference Optimization (MOPO), a constrained KL-regularized framework that maximizes a primary objective while enforcing lower bounds on secondary objec","authors_text":"Akhil Agnihotri, Deepak Ramachandran, Rahul Jain, Zheng Wen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T05:58:26Z","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10892","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":"sha256:17c8596f7b686cfa0394b8654dc9a10372377ce561e493d066cb2b25fed7b1e8","target":"record","created_at":"2026-06-08T01:03:44Z","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":"9fc854972dd4426d88776975c6cd4fd9bcd1ad93f9a437b4a37d7b862db726b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T05:58:26Z","title_canon_sha256":"cc1905f928e4d4bb331fb771ffcb6819d96a47c161bc473d41d6229e77786cf9"},"schema_version":"1.0","source":{"id":"2505.10892","kind":"arxiv","version":2}},"canonical_sha256":"396542d6178cb5c49eed3c1f754c768b4e35378cde1576d466d4e65781f27191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"396542d6178cb5c49eed3c1f754c768b4e35378cde1576d466d4e65781f27191","first_computed_at":"2026-06-08T01:03:44.422455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:44.422455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N+NAAMLAMQfdQeaFEu1vEac8z1J0pXeiNbfzBDWExtntPB35is9Y4ih9S7gqG0/qEt6RrAvMZG9vaPvu/itXCg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:44.423454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10892","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17c8596f7b686cfa0394b8654dc9a10372377ce561e493d066cb2b25fed7b1e8","sha256:d93c7ad14957f170aec6fbb04430f288d771e12293f6c609854f13755a8848fd"],"state_sha256":"20ff4bf22f41e55bbb8186d28e021e0a71c531438eb40c5fa5c4c9a42476822a"}