{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EIO4PKYHWIDZDIG4VTEC7PENO4","short_pith_number":"pith:EIO4PKYH","schema_version":"1.0","canonical_sha256":"221dc7ab07b20791a0dcacc82fbc8d77231ea0925ba398e4556bd929505eea10","source":{"kind":"arxiv","id":"2010.06313","version":2},"attestation_state":"computed","paper":{"title":"Controllable Pareto Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qingfu Zhang, Sam Kwong, Xi Lin, Zhiyuan Yang","submitted_at":"2020-10-13T11:53:55Z","abstract_excerpt":"A multi-task learning (MTL) system aims at solving multiple related tasks at the same time. With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together. For many real-world applications where the trade-off has to be made online, multiple models with different preferences over tasks have to be trained and stored. This work proposes a novel controllable Pareto multi-task learning framework, to enable the system to make real-time trade-off control among different tasks with a single model. To be spe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.06313","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-13T11:53:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9b5aa653390e559a1bae7299c3f8af9dd15230d61d732ed4088b9d0f86ad3496","abstract_canon_sha256":"b1177a61b6aca71d549e7bb502627a678e7232410522cf5d36d4ff360d09df4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:11.825246Z","signature_b64":"nPBDCFUspb5FjRPluqDt3HEQ3OqkvFveLO28N/CM9z9ZAbGZ2y9QGnGtqOyJSUFasnHyhCcPZpalJtlaIYMVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"221dc7ab07b20791a0dcacc82fbc8d77231ea0925ba398e4556bd929505eea10","last_reissued_at":"2026-07-05T02:15:11.824761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:11.824761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Pareto Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qingfu Zhang, Sam Kwong, Xi Lin, Zhiyuan Yang","submitted_at":"2020-10-13T11:53:55Z","abstract_excerpt":"A multi-task learning (MTL) system aims at solving multiple related tasks at the same time. With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together. For many real-world applications where the trade-off has to be made online, multiple models with different preferences over tasks have to be trained and stored. This work proposes a novel controllable Pareto multi-task learning framework, to enable the system to make real-time trade-off control among different tasks with a single model. To be spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06313","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/2010.06313/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.06313","created_at":"2026-07-05T02:15:11.824819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06313v2","created_at":"2026-07-05T02:15:11.824819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06313","created_at":"2026-07-05T02:15:11.824819+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIO4PKYHWIDZ","created_at":"2026-07-05T02:15:11.824819+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIO4PKYHWIDZDIG4","created_at":"2026-07-05T02:15:11.824819+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIO4PKYH","created_at":"2026-07-05T02:15:11.824819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01712","citing_title":"CoAction: Cross-task Correlation-aware Pareto Set Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01712","citing_title":"CoAction: Cross-task Correlation-aware Pareto Set Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4","json":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4.json","graph_json":"https://pith.science/api/pith-number/EIO4PKYHWIDZDIG4VTEC7PENO4/graph.json","events_json":"https://pith.science/api/pith-number/EIO4PKYHWIDZDIG4VTEC7PENO4/events.json","paper":"https://pith.science/paper/EIO4PKYH"},"agent_actions":{"view_html":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4","download_json":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4.json","view_paper":"https://pith.science/paper/EIO4PKYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06313&json=true","fetch_graph":"https://pith.science/api/pith-number/EIO4PKYHWIDZDIG4VTEC7PENO4/graph.json","fetch_events":"https://pith.science/api/pith-number/EIO4PKYHWIDZDIG4VTEC7PENO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4/action/storage_attestation","attest_author":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4/action/author_attestation","sign_citation":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4/action/citation_signature","submit_replication":"https://pith.science/pith/EIO4PKYHWIDZDIG4VTEC7PENO4/action/replication_record"}},"created_at":"2026-07-05T02:15:11.824819+00:00","updated_at":"2026-07-05T02:15:11.824819+00:00"}