{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GZQVH2GVLDTZS2FPIZRD4ZNBDR","short_pith_number":"pith:GZQVH2GV","canonical_record":{"source":{"id":"2210.12624","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T05:54:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"529355f9d70d1b368d1a48c90bd150ea16b1cfdee47c19fb6f5bf2dbaf74b8d8","abstract_canon_sha256":"be89dcc8e1aed48a496b87f398d3ebfd01d2341fa1c908df8d58ce6a43e5b4aa"},"schema_version":"1.0"},"canonical_sha256":"366153e8d558e79968af46623e65a11c55b6a6a6053692c4f0c2c77428f58ae9","source":{"kind":"arxiv","id":"2210.12624","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12624","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12624v2","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12624","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"GZQVH2GVLDTZ","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"GZQVH2GVLDTZS2FP","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"GZQVH2GV","created_at":"2026-07-05T07:57:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GZQVH2GVLDTZS2FPIZRD4ZNBDR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.12624","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T05:54:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"529355f9d70d1b368d1a48c90bd150ea16b1cfdee47c19fb6f5bf2dbaf74b8d8","abstract_canon_sha256":"be89dcc8e1aed48a496b87f398d3ebfd01d2341fa1c908df8d58ce6a43e5b4aa"},"schema_version":"1.0"},"canonical_sha256":"366153e8d558e79968af46623e65a11c55b6a6a6053692c4f0c2c77428f58ae9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:38.545515Z","signature_b64":"TH4rhW+FgrupURsqOD001FCxtPYIo8W+Eq3YuQ9u1RHVKcPt17Oy1SXdulvbKPDbd1cUyH24ShUvK54QqPAAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"366153e8d558e79968af46623e65a11c55b6a6a6053692c4f0c2c77428f58ae9","last_reissued_at":"2026-07-05T07:57:38.545082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:38.545082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.12624","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":"2026-07-05T07:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZL1UgbLCqkTFdzgmqv6YdhS8YLbCt7+B9t3PqdBuwhUbNCeYFFlA60EcISbpUygBdR9y2kzQr60ngJmCR1QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:39:02.384972Z"},"content_sha256":"8ef46479bf0789dd44c9e10c04b33a9e62c72fabe8d389dc8fa86d9bd6b6c24a","schema_version":"1.0","event_id":"sha256:8ef46479bf0789dd44c9e10c04b33a9e62c72fabe8d389dc8fa86d9bd6b6c24a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GZQVH2GVLDTZS2FPIZRD4ZNBDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Shen, Heshan Fernando, Keerthiram Murugesan, Miao Liu, Subhajit Chaudhury, Tianyi Chen","submitted_at":"2022-10-23T05:54:26Z","abstract_excerpt":"Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them. This problems are often tackled by the multi-objective optimization framework. However, existing stochastic multi-objective gradient methods and its variants (e.g., MGDA, PCGrad, CAGrad, etc.) all adopt a biased noisy gradient direction, which leads to degraded empiri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12624","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/2210.12624/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":"2026-07-05T07:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XxBpL+1QiSdtsl8uUV9Bg60w7/PhUEDeW36arOOoqGY7V0foXUNoMV2NuRJIHRnvoTKlMgoc3GIHfShXPn5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:39:02.385526Z"},"content_sha256":"c2d265854e44d4847fb38001a11059b30be03b9623369a731ef525f8dc345857","schema_version":"1.0","event_id":"sha256:c2d265854e44d4847fb38001a11059b30be03b9623369a731ef525f8dc345857"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/bundle.json","state_url":"https://pith.science/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/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":"2026-08-17T13:39:02Z","links":{"resolver":"https://pith.science/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR","bundle":"https://pith.science/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/bundle.json","state":"https://pith.science/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZQVH2GVLDTZS2FPIZRD4ZNBDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GZQVH2GVLDTZS2FPIZRD4ZNBDR","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":"be89dcc8e1aed48a496b87f398d3ebfd01d2341fa1c908df8d58ce6a43e5b4aa","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T05:54:26Z","title_canon_sha256":"529355f9d70d1b368d1a48c90bd150ea16b1cfdee47c19fb6f5bf2dbaf74b8d8"},"schema_version":"1.0","source":{"id":"2210.12624","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12624","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12624v2","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12624","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"GZQVH2GVLDTZ","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"GZQVH2GVLDTZS2FP","created_at":"2026-07-05T07:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"GZQVH2GV","created_at":"2026-07-05T07:57:38Z"}],"graph_snapshots":[{"event_id":"sha256:c2d265854e44d4847fb38001a11059b30be03b9623369a731ef525f8dc345857","target":"graph","created_at":"2026-07-05T07:57:38Z","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/2210.12624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them. This problems are often tackled by the multi-objective optimization framework. However, existing stochastic multi-objective gradient methods and its variants (e.g., MGDA, PCGrad, CAGrad, etc.) all adopt a biased noisy gradient direction, which leads to degraded empiri","authors_text":"Han Shen, Heshan Fernando, Keerthiram Murugesan, Miao Liu, Subhajit Chaudhury, Tianyi Chen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T05:54:26Z","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12624","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":"sha256:8ef46479bf0789dd44c9e10c04b33a9e62c72fabe8d389dc8fa86d9bd6b6c24a","target":"record","created_at":"2026-07-05T07:57:38Z","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":"be89dcc8e1aed48a496b87f398d3ebfd01d2341fa1c908df8d58ce6a43e5b4aa","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T05:54:26Z","title_canon_sha256":"529355f9d70d1b368d1a48c90bd150ea16b1cfdee47c19fb6f5bf2dbaf74b8d8"},"schema_version":"1.0","source":{"id":"2210.12624","kind":"arxiv","version":2}},"canonical_sha256":"366153e8d558e79968af46623e65a11c55b6a6a6053692c4f0c2c77428f58ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"366153e8d558e79968af46623e65a11c55b6a6a6053692c4f0c2c77428f58ae9","first_computed_at":"2026-07-05T07:57:38.545082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:38.545082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TH4rhW+FgrupURsqOD001FCxtPYIo8W+Eq3YuQ9u1RHVKcPt17Oy1SXdulvbKPDbd1cUyH24ShUvK54QqPAAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:38.545515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12624","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ef46479bf0789dd44c9e10c04b33a9e62c72fabe8d389dc8fa86d9bd6b6c24a","sha256:c2d265854e44d4847fb38001a11059b30be03b9623369a731ef525f8dc345857"],"state_sha256":"a5e119e922e7983f00d9cbf072dcc8df92ae5b82306f16f9c235d10b5b19d020"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bHYVOxOYI/tEPp3lGptAZ9I0/zTxc6dB0L/LoBzg97Jcl9QgPN5UUWcWohKLqo1ob+DEuTwaChhHuIZCpgoJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:39:02.389044Z","bundle_sha256":"b2dcb5be5812d515f458af4aee1ef950df87662c00148227441ff0dd44b28fe4"}}