{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C442RACIC74MGHXAEV56ED3WZO","short_pith_number":"pith:C442RACI","canonical_record":{"source":{"id":"2503.10669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T09:52:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"424b371ad21762c5f1da93df7644713ac582fd285584a5981406d6e4de6cdde2","abstract_canon_sha256":"e83125511944592c758f8f55257f447e56a25004bfdf423a98ccefbb6c198866"},"schema_version":"1.0"},"canonical_sha256":"1739a8804817f8c31ee0257be20f76cbaa3b2c4168cb7c07c87da7045c47b5c4","source":{"kind":"arxiv","id":"2503.10669","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10669","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10669v2","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10669","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"C442RACIC74M","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"C442RACIC74MGHXA","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"C442RACI","created_at":"2026-07-05T11:04:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C442RACIC74MGHXAEV56ED3WZO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T09:52:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"424b371ad21762c5f1da93df7644713ac582fd285584a5981406d6e4de6cdde2","abstract_canon_sha256":"e83125511944592c758f8f55257f447e56a25004bfdf423a98ccefbb6c198866"},"schema_version":"1.0"},"canonical_sha256":"1739a8804817f8c31ee0257be20f76cbaa3b2c4168cb7c07c87da7045c47b5c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:47.217705Z","signature_b64":"olkrsBdJ+RZM/qVVKbRMHGfH8+rfZt4IrNNwPf1EDklN1UaJ++KyXXGQtXX1tqreTcYr/+TdLr4JkKaJ3RrcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1739a8804817f8c31ee0257be20f76cbaa3b2c4168cb7c07c87da7045c47b5c4","last_reissued_at":"2026-07-05T11:04:47.217145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:47.217145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10669","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffQVIB934bhH80FQK6d6OdACaFgPedVWrwg50vllbbz4Lt1EyKW22Z7+oMerW4TSDw99joGlRXlDkaz4E9tACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:11:22.768788Z"},"content_sha256":"6834932a1a2d244115f1ea02f1fd34fab818592c3f627dcf5f1bc45665b0a9ae","schema_version":"1.0","event_id":"sha256:6834932a1a2d244115f1ea02f1fd34fab818592c3f627dcf5f1bc45665b0a9ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C442RACIC74MGHXAEV56ED3WZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boming Yang, Masashi Sugiyama, Pushi Zhang, Xin-Qiang Cai, Xinyu Xing, Yuting Tang, Zelei Cheng","submitted_at":"2025-03-10T09:52:42Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences. Methods such as RiC that directly inject raw reward values into prompts face significant numerical sensitivity issues--for instance, LLMs may fail to distinguish between 9.11 and 9.8--while alternatives like MORLHF, Rewarded Soups, and MODPO incur high computational costs by training multiple models. In this work, we introduce Utility-Conditione"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10669","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.10669/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j++t3OfbS1ORqRpzrrmhp0LZeQxO9nSMdz0rfOb8PH9cBktL/3wOHs+QxDNnjxheVKsuRhvsMzNK91n0Q4XiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:11:22.769157Z"},"content_sha256":"7ec648cc5077760b08fdb9e7c1869efb09dbf3d748c9189b4efa6bd3f58b7266","schema_version":"1.0","event_id":"sha256:7ec648cc5077760b08fdb9e7c1869efb09dbf3d748c9189b4efa6bd3f58b7266"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C442RACIC74MGHXAEV56ED3WZO/bundle.json","state_url":"https://pith.science/pith/C442RACIC74MGHXAEV56ED3WZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C442RACIC74MGHXAEV56ED3WZO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T00:11:22Z","links":{"resolver":"https://pith.science/pith/C442RACIC74MGHXAEV56ED3WZO","bundle":"https://pith.science/pith/C442RACIC74MGHXAEV56ED3WZO/bundle.json","state":"https://pith.science/pith/C442RACIC74MGHXAEV56ED3WZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C442RACIC74MGHXAEV56ED3WZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C442RACIC74MGHXAEV56ED3WZO","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":"e83125511944592c758f8f55257f447e56a25004bfdf423a98ccefbb6c198866","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T09:52:42Z","title_canon_sha256":"424b371ad21762c5f1da93df7644713ac582fd285584a5981406d6e4de6cdde2"},"schema_version":"1.0","source":{"id":"2503.10669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10669","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10669v2","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10669","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"C442RACIC74M","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"C442RACIC74MGHXA","created_at":"2026-07-05T11:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"C442RACI","created_at":"2026-07-05T11:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:7ec648cc5077760b08fdb9e7c1869efb09dbf3d748c9189b4efa6bd3f58b7266","target":"graph","created_at":"2026-07-05T11:04:47Z","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/2503.10669/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 become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences. Methods such as RiC that directly inject raw reward values into prompts face significant numerical sensitivity issues--for instance, LLMs may fail to distinguish between 9.11 and 9.8--while alternatives like MORLHF, Rewarded Soups, and MODPO incur high computational costs by training multiple models. In this work, we introduce Utility-Conditione","authors_text":"Boming Yang, Masashi Sugiyama, Pushi Zhang, Xin-Qiang Cai, Xinyu Xing, Yuting Tang, Zelei Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T09:52:42Z","title":"UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10669","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":"sha256:6834932a1a2d244115f1ea02f1fd34fab818592c3f627dcf5f1bc45665b0a9ae","target":"record","created_at":"2026-07-05T11:04:47Z","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":"e83125511944592c758f8f55257f447e56a25004bfdf423a98ccefbb6c198866","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T09:52:42Z","title_canon_sha256":"424b371ad21762c5f1da93df7644713ac582fd285584a5981406d6e4de6cdde2"},"schema_version":"1.0","source":{"id":"2503.10669","kind":"arxiv","version":2}},"canonical_sha256":"1739a8804817f8c31ee0257be20f76cbaa3b2c4168cb7c07c87da7045c47b5c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1739a8804817f8c31ee0257be20f76cbaa3b2c4168cb7c07c87da7045c47b5c4","first_computed_at":"2026-07-05T11:04:47.217145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:47.217145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"olkrsBdJ+RZM/qVVKbRMHGfH8+rfZt4IrNNwPf1EDklN1UaJ++KyXXGQtXX1tqreTcYr/+TdLr4JkKaJ3RrcCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:47.217705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6834932a1a2d244115f1ea02f1fd34fab818592c3f627dcf5f1bc45665b0a9ae","sha256:7ec648cc5077760b08fdb9e7c1869efb09dbf3d748c9189b4efa6bd3f58b7266"],"state_sha256":"957cc839399b1e7f072dafced76b8019c22c0eed8628ed96dcef5d51e9658342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"645MlggO398qhrS+fRUMmmBzc9dQWive/DAY9p+TLfXz/KSJUGZdwgkLyPtZMEk9qnDC5SFvHaKhoE3gsCxEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:11:22.771101Z","bundle_sha256":"28914b414acdac0f94edc782922ee5ef2f151b65f1213866d45b41a47d3694c8"}}