{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4OL4ZDCU22CLA6ESJYYVZLMQZK","short_pith_number":"pith:4OL4ZDCU","canonical_record":{"source":{"id":"2403.16162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-24T14:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"7369d4db4104382797124fcd018a5dfbcb0af97b2e5b9547bc69831f76fc12c0","abstract_canon_sha256":"17fbd76812ffe4a8b3c786b647814c2ed2a176ef2fb101ee0d5ff9826665b961"},"schema_version":"1.0"},"canonical_sha256":"e397cc8c54d684b078924e315cad90cab174ce8ee95aa02fc1f46285ba810a29","source":{"kind":"arxiv","id":"2403.16162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16162","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16162v1","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16162","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"4OL4ZDCU22CL","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"4OL4ZDCU22CLA6ES","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"4OL4ZDCU","created_at":"2026-07-05T08:00:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4OL4ZDCU22CLA6ESJYYVZLMQZK","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-24T14:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"7369d4db4104382797124fcd018a5dfbcb0af97b2e5b9547bc69831f76fc12c0","abstract_canon_sha256":"17fbd76812ffe4a8b3c786b647814c2ed2a176ef2fb101ee0d5ff9826665b961"},"schema_version":"1.0"},"canonical_sha256":"e397cc8c54d684b078924e315cad90cab174ce8ee95aa02fc1f46285ba810a29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:11.364328Z","signature_b64":"r1g2pLVGIIUyx+Jez8U7V9F8G+ekqWI83E4ADBy03I++TPL/KpEERxx8Nh3+eKVgjEwBhFolPBDbKWsk+v0LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e397cc8c54d684b078924e315cad90cab174ce8ee95aa02fc1f46285ba810a29","last_reissued_at":"2026-07-05T08:00:11.363880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:11.363880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16162","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":"2026-07-05T08:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9asMSbEeVsPltRqTlvWoCAhIGr3h3+g4GSwgYP+tQPXFNP1xFqTHtkOveXvKZLpXzl7JH8ZEVUpzSQKtAcO8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:01:14.415044Z"},"content_sha256":"45dfc27def291980bc5ba723c8fd6726b09d6dcdde381e4ee853ae20cb734a4a","schema_version":"1.0","event_id":"sha256:45dfc27def291980bc5ba723c8fd6726b09d6dcdde381e4ee853ae20cb734a4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4OL4ZDCU22CLA6ESJYYVZLMQZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Learning with Multi-Task Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhishek Gupta, Lu Bai, Yew-Soon Ong","submitted_at":"2024-03-24T14:04:40Z","abstract_excerpt":"Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized yet well-distributed models that collectively embody different trade-offs in one algorithmic pass, this paper proposes to view Pareto multi-task learning through the lens of multi-task optimization. Multi-task learning is first cast as a multi-objective optimization problem, which is then decomposed into a diverse set of unconstrained scalar-valued subproble"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16162","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/2403.16162/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":"2026-07-05T08:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQ/tiGWrjo8eVJK/2ChAjPgWzblkjF7AOrV0cGJj90oEBed8uFCuEns7KgMHDrcrRuc+f19H+PvrzWCbDjdPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:01:14.415606Z"},"content_sha256":"2fea2d451a6e7687379fe7162939e4041e9488046ec4eb287bd11ba287928bc7","schema_version":"1.0","event_id":"sha256:2fea2d451a6e7687379fe7162939e4041e9488046ec4eb287bd11ba287928bc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/bundle.json","state_url":"https://pith.science/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/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":"2026-08-17T23:01:14Z","links":{"resolver":"https://pith.science/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK","bundle":"https://pith.science/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/bundle.json","state":"https://pith.science/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OL4ZDCU22CLA6ESJYYVZLMQZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4OL4ZDCU22CLA6ESJYYVZLMQZK","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":"17fbd76812ffe4a8b3c786b647814c2ed2a176ef2fb101ee0d5ff9826665b961","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-24T14:04:40Z","title_canon_sha256":"7369d4db4104382797124fcd018a5dfbcb0af97b2e5b9547bc69831f76fc12c0"},"schema_version":"1.0","source":{"id":"2403.16162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16162","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16162v1","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16162","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"4OL4ZDCU22CL","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"4OL4ZDCU22CLA6ES","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"4OL4ZDCU","created_at":"2026-07-05T08:00:11Z"}],"graph_snapshots":[{"event_id":"sha256:2fea2d451a6e7687379fe7162939e4041e9488046ec4eb287bd11ba287928bc7","target":"graph","created_at":"2026-07-05T08:00:11Z","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/2403.16162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized yet well-distributed models that collectively embody different trade-offs in one algorithmic pass, this paper proposes to view Pareto multi-task learning through the lens of multi-task optimization. Multi-task learning is first cast as a multi-objective optimization problem, which is then decomposed into a diverse set of unconstrained scalar-valued subproble","authors_text":"Abhishek Gupta, Lu Bai, Yew-Soon Ong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-24T14:04:40Z","title":"Multi-Task Learning with Multi-Task Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16162","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":"sha256:45dfc27def291980bc5ba723c8fd6726b09d6dcdde381e4ee853ae20cb734a4a","target":"record","created_at":"2026-07-05T08:00:11Z","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":"17fbd76812ffe4a8b3c786b647814c2ed2a176ef2fb101ee0d5ff9826665b961","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-24T14:04:40Z","title_canon_sha256":"7369d4db4104382797124fcd018a5dfbcb0af97b2e5b9547bc69831f76fc12c0"},"schema_version":"1.0","source":{"id":"2403.16162","kind":"arxiv","version":1}},"canonical_sha256":"e397cc8c54d684b078924e315cad90cab174ce8ee95aa02fc1f46285ba810a29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e397cc8c54d684b078924e315cad90cab174ce8ee95aa02fc1f46285ba810a29","first_computed_at":"2026-07-05T08:00:11.363880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:11.363880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r1g2pLVGIIUyx+Jez8U7V9F8G+ekqWI83E4ADBy03I++TPL/KpEERxx8Nh3+eKVgjEwBhFolPBDbKWsk+v0LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:11.364328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45dfc27def291980bc5ba723c8fd6726b09d6dcdde381e4ee853ae20cb734a4a","sha256:2fea2d451a6e7687379fe7162939e4041e9488046ec4eb287bd11ba287928bc7"],"state_sha256":"11b2fc2d2093c5b95675927cb827e42e0dd29ef0822259b3abd83e971bf980a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqrRlCOWov1nsK++DguNd9ASLRR4lm6N1Mn8A45d3dyfY92PIvZOrJjWHwF+Bx8c10RZEjJa5YBq8iaqOwubBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:01:14.421148Z","bundle_sha256":"6633fdb86877cee9c35d4a7c2a3ae08faafa7bada4f56d36a8aba98473921add"}}