{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MDGCVOT5NN5CKOQ74P6EFKUACZ","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":"40864f0267d246039297d5308208bed8b2ec161dc1e08d871a3755b3bc465b21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:25:26Z","title_canon_sha256":"db3756dc78f3d608df2e487cdd6295ee2b56134e5b51f3c8d39c7bb68d64743e"},"schema_version":"1.0","source":{"id":"2507.01915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01915","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01915v1","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01915","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_12","alias_value":"MDGCVOT5NN5C","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"MDGCVOT5NN5CKOQ7","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"MDGCVOT5","created_at":"2026-07-05T11:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:0ca1fd0e683f759e4e20adc89499b0932537eb07a46bba398298895f76fd123a","target":"graph","created_at":"2026-07-05T11:30:58Z","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/2507.01915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant challenge, particularly when they are conflict. To address this issue, we frame human value alignment as a multi-objective optimization problem, aiming to maximize a set of potentially conflicting objectives. We introduce Gradient-Adaptive Policy Optimization (GAPO), a novel fine-tuning paradigm that employs multiple-gradient descent to align LLMs with diver","authors_text":"Chengao Li, Hanyu Zhang, Hongyan Xue, Qing He, Xiang Ao, Yunkun Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:25:26Z","title":"Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01915","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:f6d0bba6a871f17efa73773bbbb1424a34c8530d2da7ebafb9625bd4380fd656","target":"record","created_at":"2026-07-05T11:30:58Z","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":"40864f0267d246039297d5308208bed8b2ec161dc1e08d871a3755b3bc465b21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:25:26Z","title_canon_sha256":"db3756dc78f3d608df2e487cdd6295ee2b56134e5b51f3c8d39c7bb68d64743e"},"schema_version":"1.0","source":{"id":"2507.01915","kind":"arxiv","version":1}},"canonical_sha256":"60cc2aba7d6b7a253a1fe3fc42aa801677fb05322b81788907502945d6751697","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60cc2aba7d6b7a253a1fe3fc42aa801677fb05322b81788907502945d6751697","first_computed_at":"2026-07-05T11:30:58.062820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:58.062820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tWqpSSAMWYoduSDNBP+o3P+Ex5cS7CrVvNKxIJm8xKi3gj8jw8NzbSZlcE9dKPvwPVbYIzIH0j+eNwUhoYzNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:58.063311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6d0bba6a871f17efa73773bbbb1424a34c8530d2da7ebafb9625bd4380fd656","sha256:0ca1fd0e683f759e4e20adc89499b0932537eb07a46bba398298895f76fd123a"],"state_sha256":"744e4745adec2baf462e59bf3818b7025bf854c650b683e71942a0a3b34f97d4"}