{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TEFXQDUFIV7ZLY67RUJJRHAR5K","short_pith_number":"pith:TEFXQDUF","canonical_record":{"source":{"id":"2504.02854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-26T16:41:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cec6078bb4afe5aabdabc23f612e20e2ff3c7e1f5d254910b1606afbc5a1e61","abstract_canon_sha256":"ad68a5b5ec58009b630756f98f38f66d2515b28b245f725da4ded57af5803fe6"},"schema_version":"1.0"},"canonical_sha256":"990b780e85457f95e3df8d12989c11ea92ba8014877148a2e9f3fa14d7a1bf81","source":{"kind":"arxiv","id":"2504.02854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02854","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02854v1","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02854","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"TEFXQDUFIV7Z","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"TEFXQDUFIV7ZLY67","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"TEFXQDUF","created_at":"2026-07-05T10:44:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TEFXQDUFIV7ZLY67RUJJRHAR5K","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-26T16:41:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cec6078bb4afe5aabdabc23f612e20e2ff3c7e1f5d254910b1606afbc5a1e61","abstract_canon_sha256":"ad68a5b5ec58009b630756f98f38f66d2515b28b245f725da4ded57af5803fe6"},"schema_version":"1.0"},"canonical_sha256":"990b780e85457f95e3df8d12989c11ea92ba8014877148a2e9f3fa14d7a1bf81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:03.954123Z","signature_b64":"3VWauYmG0ei5b3cUOnYGc2ZZkA5DomFHgUBdfVI0vmRRrqIZPTEZ5T/P3sAffIciNj7yBF2Y8YbBo8jSlE5GBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"990b780e85457f95e3df8d12989c11ea92ba8014877148a2e9f3fa14d7a1bf81","last_reissued_at":"2026-07-05T10:44:03.953661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:03.953661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02854","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hBd+CFG5gguW+X65B7IVNKVDP56aBQDNG2Q5LBVX4DOCDz+RX3pBX9ZUWZHd9mvpXgC8UfV+U3AHJyvTkiFnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:06:21.709390Z"},"content_sha256":"7edb1267e6569918b135509cc3159be9f4f2c332d0980ef85d8de8d2168831d3","schema_version":"1.0","event_id":"sha256:7edb1267e6569918b135509cc3159be9f4f2c332d0980ef85d8de8d2168831d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TEFXQDUFIV7ZLY67RUJJRHAR5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ellen Hidemi Fukuda, Kun Yuan, Lisha Chen, Quan Xiao, Tianyi Chen, Xinyi Chen","submitted_at":"2025-03-26T16:41:07Z","abstract_excerpt":"Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose goal is to optimize a pre-defined preference function, subject to the constraint that the model parameters are weakly Pareto optimal. To solve this problem, we convert the multi-objective constraints to a single-objective constraint through a merit function with an easy-to-evaluate gradient, and then, we use a penalty-based reformulation of the bilevel optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02854","kind":"arxiv","version":1},"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/2504.02854/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":"2026-07-05T10:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74mbrHoaWEW4PKWj15NeDVsHIOdFnmPNRAeEDyR5mwxeqpmyX04k/eNUqrcEgkURbrrcnArHJ3b9hVyhq6fvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:06:21.709895Z"},"content_sha256":"5126786d2c50dce11d591670a3689e6bf33648677428a6815b5c915e314ee900","schema_version":"1.0","event_id":"sha256:5126786d2c50dce11d591670a3689e6bf33648677428a6815b5c915e314ee900"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/bundle.json","state_url":"https://pith.science/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/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":"2026-08-22T12:06:21Z","links":{"resolver":"https://pith.science/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K","bundle":"https://pith.science/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/bundle.json","state":"https://pith.science/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEFXQDUFIV7ZLY67RUJJRHAR5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEFXQDUFIV7ZLY67RUJJRHAR5K","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":"ad68a5b5ec58009b630756f98f38f66d2515b28b245f725da4ded57af5803fe6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-26T16:41:07Z","title_canon_sha256":"5cec6078bb4afe5aabdabc23f612e20e2ff3c7e1f5d254910b1606afbc5a1e61"},"schema_version":"1.0","source":{"id":"2504.02854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02854","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02854v1","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02854","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"TEFXQDUFIV7Z","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"TEFXQDUFIV7ZLY67","created_at":"2026-07-05T10:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"TEFXQDUF","created_at":"2026-07-05T10:44:03Z"}],"graph_snapshots":[{"event_id":"sha256:5126786d2c50dce11d591670a3689e6bf33648677428a6815b5c915e314ee900","target":"graph","created_at":"2026-07-05T10:44:03Z","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/2504.02854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose goal is to optimize a pre-defined preference function, subject to the constraint that the model parameters are weakly Pareto optimal. To solve this problem, we convert the multi-objective constraints to a single-objective constraint through a merit function with an easy-to-evaluate gradient, and then, we use a penalty-based reformulation of the bilevel optim","authors_text":"Ellen Hidemi Fukuda, Kun Yuan, Lisha Chen, Quan Xiao, Tianyi Chen, Xinyi Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-26T16:41:07Z","title":"Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02854","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":"sha256:7edb1267e6569918b135509cc3159be9f4f2c332d0980ef85d8de8d2168831d3","target":"record","created_at":"2026-07-05T10:44:03Z","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":"ad68a5b5ec58009b630756f98f38f66d2515b28b245f725da4ded57af5803fe6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-26T16:41:07Z","title_canon_sha256":"5cec6078bb4afe5aabdabc23f612e20e2ff3c7e1f5d254910b1606afbc5a1e61"},"schema_version":"1.0","source":{"id":"2504.02854","kind":"arxiv","version":1}},"canonical_sha256":"990b780e85457f95e3df8d12989c11ea92ba8014877148a2e9f3fa14d7a1bf81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"990b780e85457f95e3df8d12989c11ea92ba8014877148a2e9f3fa14d7a1bf81","first_computed_at":"2026-07-05T10:44:03.953661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:03.953661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3VWauYmG0ei5b3cUOnYGc2ZZkA5DomFHgUBdfVI0vmRRrqIZPTEZ5T/P3sAffIciNj7yBF2Y8YbBo8jSlE5GBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:03.954123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7edb1267e6569918b135509cc3159be9f4f2c332d0980ef85d8de8d2168831d3","sha256:5126786d2c50dce11d591670a3689e6bf33648677428a6815b5c915e314ee900"],"state_sha256":"3d4b1f49af02a30cd3a370854bb1d22d8ae44496608e51cf2bc0be51182d18f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEZjdUhJQZiMGTPIOsVTKaUcE1Sgmh6txbtD60I2O7btlvicZq82BpzsbHo1vIn9hBCVWlj4nZ65bJV72rMuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:06:21.714475Z","bundle_sha256":"bcc3fb06e1ba1337cf519fa2d50298eac2d01d91244431819f3172d86eb1ba25"}}