{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24URQGVZKJY5CQMI3D2VV57LGF","short_pith_number":"pith:24URQGVZ","schema_version":"1.0","canonical_sha256":"d729181ab95271d14188d8f55af7eb315c71e2a3ae64f77490033ea761255d6f","source":{"kind":"arxiv","id":"2402.15328","version":2},"attestation_state":"computed","paper":{"title":"Towards Principled Task Grouping for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Tianshu Yu, Xuanhao Pan","submitted_at":"2024-02-23T13:51:20Z","abstract_excerpt":"Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder performance improvements. Task grouping addresses this challenge by organizing tasks into meaningful clusters, maximizing beneficial transfer while minimizing detrimental interactions. This paper introduces a principled approach to task grouping in MTL, advancing beyond existing methods by addressing key theoretical and practical limitations. Unlike prior studies, "},"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":"2402.15328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T13:51:20Z","cross_cats_sorted":[],"title_canon_sha256":"4b6f8efaf8d218bbfe0be4d24c88183989a6cd34f4f8f58ee8c6f918731f6e98","abstract_canon_sha256":"cfe3f79aa662257cb06d7e63d33c425920a060db0cefdb86339c9ac13c303889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:49.075395Z","signature_b64":"AV1ZrMWWBC4UACFAeK4ll1iEHdoCq3ht19d87aVjzDORS2HRayXBET+FHqFbHWFMFS0akEtskBJwtDHz+4uRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d729181ab95271d14188d8f55af7eb315c71e2a3ae64f77490033ea761255d6f","last_reissued_at":"2026-07-05T11:03:49.074878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:49.074878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Principled Task Grouping for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Tianshu Yu, Xuanhao Pan","submitted_at":"2024-02-23T13:51:20Z","abstract_excerpt":"Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder performance improvements. Task grouping addresses this challenge by organizing tasks into meaningful clusters, maximizing beneficial transfer while minimizing detrimental interactions. This paper introduces a principled approach to task grouping in MTL, advancing beyond existing methods by addressing key theoretical and practical limitations. Unlike prior studies, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15328","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/2402.15328/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":"2402.15328","created_at":"2026-07-05T11:03:49.074935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15328v2","created_at":"2026-07-05T11:03:49.074935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15328","created_at":"2026-07-05T11:03:49.074935+00:00"},{"alias_kind":"pith_short_12","alias_value":"24URQGVZKJY5","created_at":"2026-07-05T11:03:49.074935+00:00"},{"alias_kind":"pith_short_16","alias_value":"24URQGVZKJY5CQMI","created_at":"2026-07-05T11:03:49.074935+00:00"},{"alias_kind":"pith_short_8","alias_value":"24URQGVZ","created_at":"2026-07-05T11:03:49.074935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06877","citing_title":"CDC: Causal Domain Clustering for Multi-Domain Recommendation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF","json":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF.json","graph_json":"https://pith.science/api/pith-number/24URQGVZKJY5CQMI3D2VV57LGF/graph.json","events_json":"https://pith.science/api/pith-number/24URQGVZKJY5CQMI3D2VV57LGF/events.json","paper":"https://pith.science/paper/24URQGVZ"},"agent_actions":{"view_html":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF","download_json":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF.json","view_paper":"https://pith.science/paper/24URQGVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15328&json=true","fetch_graph":"https://pith.science/api/pith-number/24URQGVZKJY5CQMI3D2VV57LGF/graph.json","fetch_events":"https://pith.science/api/pith-number/24URQGVZKJY5CQMI3D2VV57LGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF/action/storage_attestation","attest_author":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF/action/author_attestation","sign_citation":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF/action/citation_signature","submit_replication":"https://pith.science/pith/24URQGVZKJY5CQMI3D2VV57LGF/action/replication_record"}},"created_at":"2026-07-05T11:03:49.074935+00:00","updated_at":"2026-07-05T11:03:49.074935+00:00"}