{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SGHNWMKDJQ357PHK2GRT4B7J3C","short_pith_number":"pith:SGHNWMKD","canonical_record":{"source":{"id":"2305.18409","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T16:13:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fab3ced339a85f33fdabd4ea38697bd8a0bced7dfa1dfebb8b4c1d40f8c32fd3","abstract_canon_sha256":"9fb899bfd1ebbca266d3eedac98f7f81f660165c4d34e92764658ade7b97d39f"},"schema_version":"1.0"},"canonical_sha256":"918edb31434c37dfbcead1a33e07e9d8bbd160f8e44d6b75a4c5682be6724a6e","source":{"kind":"arxiv","id":"2305.18409","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18409","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18409v3","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18409","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"SGHNWMKDJQ35","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"SGHNWMKDJQ357PHK","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"SGHNWMKD","created_at":"2026-07-05T07:17:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SGHNWMKDJQ357PHK2GRT4B7J3C","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18409","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T16:13:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fab3ced339a85f33fdabd4ea38697bd8a0bced7dfa1dfebb8b4c1d40f8c32fd3","abstract_canon_sha256":"9fb899bfd1ebbca266d3eedac98f7f81f660165c4d34e92764658ade7b97d39f"},"schema_version":"1.0"},"canonical_sha256":"918edb31434c37dfbcead1a33e07e9d8bbd160f8e44d6b75a4c5682be6724a6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:53.527026Z","signature_b64":"b41JLwwlHHtcdPg9+2Zo7cEtjJUzMCpOsf+MhfLaJGeM+z2Ng1PYmMfM2jmGLHDCs1ODys1i69MN+PlyisbLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918edb31434c37dfbcead1a33e07e9d8bbd160f8e44d6b75a4c5682be6724a6e","last_reissued_at":"2026-07-05T07:17:53.526538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:53.526538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18409","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJfjC+k9Ri93xEPRcE8hUz1m5Rka7A5+t+htCtW3nod+VYxkhQxCSMtPJCuoB8KqPkDz8XNodCobXIa6F7XYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:18.492245Z"},"content_sha256":"97a0216d8f863d17497096ceca7eac05a104c307540d041deda5beef84ea96d9","schema_version":"1.0","event_id":"sha256:97a0216d8f863d17497096ceca7eac05a104c307540d041deda5beef84ea96d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SGHNWMKDJQ357PHK2GRT4B7J3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Ban, Kaiyi Ji, Peiyao Xiao","submitted_at":"2023-05-28T16:13:59Z","abstract_excerpt":"Multi-objective optimization (MOO) has become an influential framework in many machine learning problems with multiple objectives such as learning with multiple criteria and multi-task learning (MTL). In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL. This formulation includes GD and MGDA as special cases, enjoys the direction-oriented benefit as in CAGrad, and facilitates the design of stochastic algorithms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18409","kind":"arxiv","version":3},"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/2305.18409/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":"2026-07-05T07:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PO+/kffpSCGLBa9BpuO7zrsi29FMAu5RZjAhxAYvXB9iRWeTi+bpNxANPCT+G2vpqtYkhnMCFVRqMisVLKNeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:18.509278Z"},"content_sha256":"718ad3e09a9557abe0d9b4fefaa3cea2374f3f2e985899a82221ac4adcc17eff","schema_version":"1.0","event_id":"sha256:718ad3e09a9557abe0d9b4fefaa3cea2374f3f2e985899a82221ac4adcc17eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/bundle.json","state_url":"https://pith.science/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/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":"2026-08-04T06:06:18Z","links":{"resolver":"https://pith.science/pith/SGHNWMKDJQ357PHK2GRT4B7J3C","bundle":"https://pith.science/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/bundle.json","state":"https://pith.science/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGHNWMKDJQ357PHK2GRT4B7J3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SGHNWMKDJQ357PHK2GRT4B7J3C","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":"9fb899bfd1ebbca266d3eedac98f7f81f660165c4d34e92764658ade7b97d39f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T16:13:59Z","title_canon_sha256":"fab3ced339a85f33fdabd4ea38697bd8a0bced7dfa1dfebb8b4c1d40f8c32fd3"},"schema_version":"1.0","source":{"id":"2305.18409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18409","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18409v3","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18409","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"SGHNWMKDJQ35","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"SGHNWMKDJQ357PHK","created_at":"2026-07-05T07:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"SGHNWMKD","created_at":"2026-07-05T07:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:718ad3e09a9557abe0d9b4fefaa3cea2374f3f2e985899a82221ac4adcc17eff","target":"graph","created_at":"2026-07-05T07:17:53Z","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/2305.18409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective optimization (MOO) has become an influential framework in many machine learning problems with multiple objectives such as learning with multiple criteria and multi-task learning (MTL). In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL. This formulation includes GD and MGDA as special cases, enjoys the direction-oriented benefit as in CAGrad, and facilitates the design of stochastic algorithms","authors_text":"Hao Ban, Kaiyi Ji, Peiyao Xiao","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T16:13:59Z","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18409","kind":"arxiv","version":3},"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":"sha256:97a0216d8f863d17497096ceca7eac05a104c307540d041deda5beef84ea96d9","target":"record","created_at":"2026-07-05T07:17:53Z","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":"9fb899bfd1ebbca266d3eedac98f7f81f660165c4d34e92764658ade7b97d39f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T16:13:59Z","title_canon_sha256":"fab3ced339a85f33fdabd4ea38697bd8a0bced7dfa1dfebb8b4c1d40f8c32fd3"},"schema_version":"1.0","source":{"id":"2305.18409","kind":"arxiv","version":3}},"canonical_sha256":"918edb31434c37dfbcead1a33e07e9d8bbd160f8e44d6b75a4c5682be6724a6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"918edb31434c37dfbcead1a33e07e9d8bbd160f8e44d6b75a4c5682be6724a6e","first_computed_at":"2026-07-05T07:17:53.526538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:53.526538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b41JLwwlHHtcdPg9+2Zo7cEtjJUzMCpOsf+MhfLaJGeM+z2Ng1PYmMfM2jmGLHDCs1ODys1i69MN+PlyisbLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:53.527026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97a0216d8f863d17497096ceca7eac05a104c307540d041deda5beef84ea96d9","sha256:718ad3e09a9557abe0d9b4fefaa3cea2374f3f2e985899a82221ac4adcc17eff"],"state_sha256":"29b841b821eb40b86883f5fe60676ea63c1fb76fa4f730c9aeadf3fd4e49d651"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KO8DLdiCvrkP9qeIAfIbb/aJER8Nm8WyrekdJgYj2WjY9kWPGotW0O4uPDP12pbDgi4SBpkhF+AQCz5TEEeBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:06:18.519328Z","bundle_sha256":"c1b890fd1e1f4f97d6a32dd87fc10d0dfd822bac92bb0aa5ac66f805a6080229"}}