{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TJQWHJIAKQMIETIHDG7RLQKMIJ","short_pith_number":"pith:TJQWHJIA","canonical_record":{"source":{"id":"2405.19440","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T18:36:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7a1d1f4906b2c40499d1deae01e8258af665876876eb3f646c514e9451bfec5e","abstract_canon_sha256":"1d4af799698b6f11fc7f2cc85feb71f3fbfb221e8640293be7040ecbd567e4a7"},"schema_version":"1.0"},"canonical_sha256":"9a6163a5005418824d0719bf15c14c427f0ed034d99ebda6fbba3dca9efbc78a","source":{"kind":"arxiv","id":"2405.19440","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19440","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19440v5","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19440","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"TJQWHJIAKQMI","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"TJQWHJIAKQMIETIH","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"TJQWHJIA","created_at":"2026-07-05T10:27:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TJQWHJIAKQMIETIHDG7RLQKMIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19440","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T18:36:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7a1d1f4906b2c40499d1deae01e8258af665876876eb3f646c514e9451bfec5e","abstract_canon_sha256":"1d4af799698b6f11fc7f2cc85feb71f3fbfb221e8640293be7040ecbd567e4a7"},"schema_version":"1.0"},"canonical_sha256":"9a6163a5005418824d0719bf15c14c427f0ed034d99ebda6fbba3dca9efbc78a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:10.690157Z","signature_b64":"sgzMsmHK9sYZzbUosUzkytpw/mxoVJwXa8svTLmIYbVsosursJYvAtWbaezb6z8vHHszhiWFR7M94hk3wn4SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a6163a5005418824d0719bf15c14c427f0ed034d99ebda6fbba3dca9efbc78a","last_reissued_at":"2026-07-05T10:27:10.689660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:10.689660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19440","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtroNCt8roHfYHvj8V1CAlWNcE0sJ5zH7+8GDhy1Vl1aK9w0Vb3FSowNCuP9tDORbxlJRWi2qmcX7GzgnD9KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:24:53.943171Z"},"content_sha256":"5bdf9c566084cf3ec93acaf7ed284b64e56e22158ffe4a20d8b8204e9774c04f","schema_version":"1.0","event_id":"sha256:5bdf9c566084cf3ec93acaf7ed284b64e56e22158ffe4a20d8b8204e9774c04f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TJQWHJIAKQMIETIHDG7RLQKMIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MGDA Converges under Generalized Smoothness, Provably","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiyi Ji, Peiyao Xiao, Qi Zhang, Shaofeng Zou","submitted_at":"2024-05-29T18:36:59Z","abstract_excerpt":"Multi-objective optimization (MOO) is receiving more attention in various fields such as multi-task learning. Recent works provide some effective algorithms with theoretical analysis but they are limited by the standard $L$-smooth or bounded-gradient assumptions, which typically do not hold for neural networks, such as Long short-term memory (LSTM) models and Transformers. In this paper, we study a more general and realistic class of generalized $\\ell$-smooth loss functions, where $\\ell$ is a general non-decreasing function of gradient norm. We revisit and analyze the fundamental multiple grad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19440","kind":"arxiv","version":5},"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/2405.19440/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":"2026-07-05T10:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbvK37JBgUpGJmuEPZxl0vqmmbyPiUdSUSJgdGshpSrVD293Nym2RuAZZP3Z924NFMCgBDwOW56zCvkheKc0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:24:53.943752Z"},"content_sha256":"da1978dcfeccb6c09abe8229509af2acd81ac7f094436c5cb165060d5eebf41f","schema_version":"1.0","event_id":"sha256:da1978dcfeccb6c09abe8229509af2acd81ac7f094436c5cb165060d5eebf41f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/bundle.json","state_url":"https://pith.science/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/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":"2026-08-03T19:24:53Z","links":{"resolver":"https://pith.science/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ","bundle":"https://pith.science/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/bundle.json","state":"https://pith.science/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJQWHJIAKQMIETIHDG7RLQKMIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TJQWHJIAKQMIETIHDG7RLQKMIJ","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":"1d4af799698b6f11fc7f2cc85feb71f3fbfb221e8640293be7040ecbd567e4a7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T18:36:59Z","title_canon_sha256":"7a1d1f4906b2c40499d1deae01e8258af665876876eb3f646c514e9451bfec5e"},"schema_version":"1.0","source":{"id":"2405.19440","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19440","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19440v5","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19440","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"TJQWHJIAKQMI","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"TJQWHJIAKQMIETIH","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"TJQWHJIA","created_at":"2026-07-05T10:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:da1978dcfeccb6c09abe8229509af2acd81ac7f094436c5cb165060d5eebf41f","target":"graph","created_at":"2026-07-05T10:27:10Z","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/2405.19440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective optimization (MOO) is receiving more attention in various fields such as multi-task learning. Recent works provide some effective algorithms with theoretical analysis but they are limited by the standard $L$-smooth or bounded-gradient assumptions, which typically do not hold for neural networks, such as Long short-term memory (LSTM) models and Transformers. In this paper, we study a more general and realistic class of generalized $\\ell$-smooth loss functions, where $\\ell$ is a general non-decreasing function of gradient norm. We revisit and analyze the fundamental multiple grad","authors_text":"Kaiyi Ji, Peiyao Xiao, Qi Zhang, Shaofeng Zou","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T18:36:59Z","title":"MGDA Converges under Generalized Smoothness, Provably"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19440","kind":"arxiv","version":5},"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":"sha256:5bdf9c566084cf3ec93acaf7ed284b64e56e22158ffe4a20d8b8204e9774c04f","target":"record","created_at":"2026-07-05T10:27:10Z","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":"1d4af799698b6f11fc7f2cc85feb71f3fbfb221e8640293be7040ecbd567e4a7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T18:36:59Z","title_canon_sha256":"7a1d1f4906b2c40499d1deae01e8258af665876876eb3f646c514e9451bfec5e"},"schema_version":"1.0","source":{"id":"2405.19440","kind":"arxiv","version":5}},"canonical_sha256":"9a6163a5005418824d0719bf15c14c427f0ed034d99ebda6fbba3dca9efbc78a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a6163a5005418824d0719bf15c14c427f0ed034d99ebda6fbba3dca9efbc78a","first_computed_at":"2026-07-05T10:27:10.689660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:10.689660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sgzMsmHK9sYZzbUosUzkytpw/mxoVJwXa8svTLmIYbVsosursJYvAtWbaezb6z8vHHszhiWFR7M94hk3wn4SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:10.690157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19440","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bdf9c566084cf3ec93acaf7ed284b64e56e22158ffe4a20d8b8204e9774c04f","sha256:da1978dcfeccb6c09abe8229509af2acd81ac7f094436c5cb165060d5eebf41f"],"state_sha256":"d0359e1c82a5ff710a812c769dbee64d83a5ed70fc0d145720c900ed40eb10d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VhI2X+EkKoFaSfrQhzRPDW45Zh0XCP1DN/+2YNlbjoYXXCA9OglmqmwliYyFqqrTcQ/+z95Nxv3nzHaxtRnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:24:53.952983Z","bundle_sha256":"25d8852a95342c7c9c78f0fca652415da7a9b11e711a0cd81113d614c248efd6"}}