{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YZPNTP7QHZK4RFMPNZLQ4MU7V","short_pith_number":"pith:3YZPNTP7","schema_version":"1.0","canonical_sha256":"de32f6cdff81f2ae44ac7b72b87194fd594df2cec909877ad7f17ee95d52c142","source":{"kind":"arxiv","id":"2402.04005","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnon Netzer, Ethan Fetaya, Gal Chechik, Idan Achituve, Idit Diamant","submitted_at":"2024-02-06T14:00:43Z","abstract_excerpt":"As machine learning becomes more prominent there is a growing demand to perform several inference tasks in parallel. Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task learning (MTL). MTL aims at learning a single model that solves several tasks efficiently. Optimizing MTL models is often achieved by computing a single gradient per task and aggregating them for obtaining a combined update direction. However, these approaches do not consider an important aspect, the sensitivity in the gradient dimensions. Here, we introduce"},"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":"2402.04005","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T14:00:43Z","cross_cats_sorted":[],"title_canon_sha256":"a34710eb495440fc7ac45a565d5cd47b0d4f3d1a164050c2fad6ee52ab04ff1e","abstract_canon_sha256":"f9b673b63b5d187714613c18f4761e26762622564c012f397b813c4b8a07fd22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:04.973618Z","signature_b64":"OBRhfWfLuNHBfxCehJca5q7lCDHy1cyiXGtJrYAiL93/DtCz6hkoQJK0AliC42NpaMVhWI6rvxQo8i1nH5/pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de32f6cdff81f2ae44ac7b72b87194fd594df2cec909877ad7f17ee95d52c142","last_reissued_at":"2026-07-05T08:18:04.973147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:04.973147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnon Netzer, Ethan Fetaya, Gal Chechik, Idan Achituve, Idit Diamant","submitted_at":"2024-02-06T14:00:43Z","abstract_excerpt":"As machine learning becomes more prominent there is a growing demand to perform several inference tasks in parallel. Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task learning (MTL). MTL aims at learning a single model that solves several tasks efficiently. Optimizing MTL models is often achieved by computing a single gradient per task and aggregating them for obtaining a combined update direction. However, these approaches do not consider an important aspect, the sensitivity in the gradient dimensions. Here, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04005","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/2402.04005/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":"2402.04005","created_at":"2026-07-05T08:18:04.973204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04005v2","created_at":"2026-07-05T08:18:04.973204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04005","created_at":"2026-07-05T08:18:04.973204+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YZPNTP7QHZK","created_at":"2026-07-05T08:18:04.973204+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YZPNTP7QHZK4RFM","created_at":"2026-07-05T08:18:04.973204+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YZPNTP7","created_at":"2026-07-05T08:18:04.973204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.18309","citing_title":"GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V","json":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V.json","graph_json":"https://pith.science/api/pith-number/3YZPNTP7QHZK4RFMPNZLQ4MU7V/graph.json","events_json":"https://pith.science/api/pith-number/3YZPNTP7QHZK4RFMPNZLQ4MU7V/events.json","paper":"https://pith.science/paper/3YZPNTP7"},"agent_actions":{"view_html":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V","download_json":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V.json","view_paper":"https://pith.science/paper/3YZPNTP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04005&json=true","fetch_graph":"https://pith.science/api/pith-number/3YZPNTP7QHZK4RFMPNZLQ4MU7V/graph.json","fetch_events":"https://pith.science/api/pith-number/3YZPNTP7QHZK4RFMPNZLQ4MU7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V/action/storage_attestation","attest_author":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V/action/author_attestation","sign_citation":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V/action/citation_signature","submit_replication":"https://pith.science/pith/3YZPNTP7QHZK4RFMPNZLQ4MU7V/action/replication_record"}},"created_at":"2026-07-05T08:18:04.973204+00:00","updated_at":"2026-07-05T08:18:04.973204+00:00"}