{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZLTGQZ2PHAKPSSJAJBHUWUV33X","short_pith_number":"pith:ZLTGQZ2P","canonical_record":{"source":{"id":"1810.04650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T17:18:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fff94599faf7b43fe283b261600e2d5411789c9566b5f54cac28444b570be27c","abstract_canon_sha256":"2dac7c4b6604083a32ff80f63a81a254f6fecc08399a4162d538b11c9a7c1c32"},"schema_version":"1.0"},"canonical_sha256":"cae668674f3814f94920484f4b52bbdde733fd44e1c1b7369f9a41b175ddd302","source":{"kind":"arxiv","id":"1810.04650","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04650","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04650v2","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04650","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZLTGQZ2PHAKP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZLTGQZ2PHAKPSSJA","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZLTGQZ2P","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZLTGQZ2PHAKPSSJAJBHUWUV33X","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T17:18:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fff94599faf7b43fe283b261600e2d5411789c9566b5f54cac28444b570be27c","abstract_canon_sha256":"2dac7c4b6604083a32ff80f63a81a254f6fecc08399a4162d538b11c9a7c1c32"},"schema_version":"1.0"},"canonical_sha256":"cae668674f3814f94920484f4b52bbdde733fd44e1c1b7369f9a41b175ddd302","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:33.452933Z","signature_b64":"twrIioWv4w7lS45KdJDk7hgLjv5WWF7CiocCV5d6wm3IXXuPhMbRwZCSUqlsEu2nY+xLAee4PIkdd61JMMaXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cae668674f3814f94920484f4b52bbdde733fd44e1c1b7369f9a41b175ddd302","last_reissued_at":"2026-05-17T23:56:33.451945Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:33.451945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04650","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":"2026-05-17T23:56:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTglfd0NsmBqkq6VmZWiwNrPxBvl9WL3X7nl4MrvZxIp05gPxSZ3TtIdsltPVzuwwc6qKc/Mj5ICi5FR61ToAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:07:21.577024Z"},"content_sha256":"3f3488720c1f90293e4a8c22085c29e700cbb7070914a20c1a8717c4eac78263","schema_version":"1.0","event_id":"sha256:3f3488720c1f90293e4a8c22085c29e700cbb7070914a20c1a8717c4eac78263"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZLTGQZ2PHAKPSSJAJBHUWUV33X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Learning as Multi-Objective Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ozan Sener, Vladlen Koltun","submitted_at":"2018-10-10T17:18:09Z","abstract_excerpt":"In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of per-task losses. However, this workaround is only valid when the tasks do not compete, which is rarely the case. In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To this end, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04650","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":""},"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":"2026-05-17T23:56:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2aac/zkWVyrFSghSSc1HS8B3ArwOiwjvQTn7w3eD5G/TQU7EtQE7KTbLSRlCbE+9IF8EnOTXDCfd5hGT3zS6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:07:21.577757Z"},"content_sha256":"8360c24d95037969365bd1cbd189f3d45e9e57014b48955b72e7c405391a42a9","schema_version":"1.0","event_id":"sha256:8360c24d95037969365bd1cbd189f3d45e9e57014b48955b72e7c405391a42a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/bundle.json","state_url":"https://pith.science/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/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":"2026-05-26T07:07:21Z","links":{"resolver":"https://pith.science/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X","bundle":"https://pith.science/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/bundle.json","state":"https://pith.science/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLTGQZ2PHAKPSSJAJBHUWUV33X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZLTGQZ2PHAKPSSJAJBHUWUV33X","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":"2dac7c4b6604083a32ff80f63a81a254f6fecc08399a4162d538b11c9a7c1c32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T17:18:09Z","title_canon_sha256":"fff94599faf7b43fe283b261600e2d5411789c9566b5f54cac28444b570be27c"},"schema_version":"1.0","source":{"id":"1810.04650","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04650","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04650v2","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04650","created_at":"2026-05-17T23:56:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZLTGQZ2PHAKP","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZLTGQZ2PHAKPSSJA","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZLTGQZ2P","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:8360c24d95037969365bd1cbd189f3d45e9e57014b48955b72e7c405391a42a9","target":"graph","created_at":"2026-05-17T23:56:33Z","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"},"paper":{"abstract_excerpt":"In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of per-task losses. However, this workaround is only valid when the tasks do not compete, which is rarely the case. In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To this end, ","authors_text":"Ozan Sener, Vladlen Koltun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T17:18:09Z","title":"Multi-Task Learning as Multi-Objective Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04650","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":"sha256:3f3488720c1f90293e4a8c22085c29e700cbb7070914a20c1a8717c4eac78263","target":"record","created_at":"2026-05-17T23:56:33Z","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":"2dac7c4b6604083a32ff80f63a81a254f6fecc08399a4162d538b11c9a7c1c32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T17:18:09Z","title_canon_sha256":"fff94599faf7b43fe283b261600e2d5411789c9566b5f54cac28444b570be27c"},"schema_version":"1.0","source":{"id":"1810.04650","kind":"arxiv","version":2}},"canonical_sha256":"cae668674f3814f94920484f4b52bbdde733fd44e1c1b7369f9a41b175ddd302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cae668674f3814f94920484f4b52bbdde733fd44e1c1b7369f9a41b175ddd302","first_computed_at":"2026-05-17T23:56:33.451945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:33.451945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twrIioWv4w7lS45KdJDk7hgLjv5WWF7CiocCV5d6wm3IXXuPhMbRwZCSUqlsEu2nY+xLAee4PIkdd61JMMaXDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:33.452933Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04650","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f3488720c1f90293e4a8c22085c29e700cbb7070914a20c1a8717c4eac78263","sha256:8360c24d95037969365bd1cbd189f3d45e9e57014b48955b72e7c405391a42a9"],"state_sha256":"d91bc7ccc1892e73f8cc9e2b4815fc2bfa1f302c9916039a085127e688a2772b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eg3ZHI+qDQpiUyxzy171ZF723EZY6/202B2XXTWQKEBBmr/eTMukRtEmazHInZidwB06o0JaUmhX6b58cBqgCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:07:21.581454Z","bundle_sha256":"18b527f7aacc78879a283f994a2343cdb9f37b0850a387168e37fcfa21d4a095"}}