{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AUS7L4G4HKYGRQFCN7IKIT4YBM","short_pith_number":"pith:AUS7L4G4","schema_version":"1.0","canonical_sha256":"0525f5f0dc3ab068c0a26fd0a44f980b2ef0c25af29f59c829bc3e2c7ab56c81","source":{"kind":"arxiv","id":"1903.12117","version":1},"attestation_state":"computed","paper":{"title":"Many Task Learning with Task Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gjorgji Strezoski, Marcel Worring, Nanne van Noord","submitted_at":"2019-03-28T17:03:04Z","abstract_excerpt":"Typical multi-task learning (MTL) methods rely on architectural adjustments and a large trainable parameter set to jointly optimize over several tasks. However, when the number of tasks increases so do the complexity of the architectural adjustments and resource requirements. In this paper, we introduce a method which applies a conditional feature-wise transformation over the convolutional activations that enables a model to successfully perform a large number of tasks. To distinguish from regular MTL, we introduce Many Task Learning (MaTL) as a special case of MTL where more than 20 tasks are"},"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":"1903.12117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-28T17:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"705ccbeee87f1cf4f5c3c4fbe95b51d271e91b0d5f858176832e04650268350b","abstract_canon_sha256":"6ebeb5e3e33974b98089951858d7582325ebe29c10aa8e7cf8e1978d613df463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:58.001450Z","signature_b64":"p0jMPCLSocdF4s8ywj/vueK0HsdMIqK+u1v34LSIXPp8GMMbMEWYafTqhGfM6epV4RItGjXpzJEOcVBXvsJlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0525f5f0dc3ab068c0a26fd0a44f980b2ef0c25af29f59c829bc3e2c7ab56c81","last_reissued_at":"2026-05-17T23:49:58.000794Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:58.000794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Many Task Learning with Task Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gjorgji Strezoski, Marcel Worring, Nanne van Noord","submitted_at":"2019-03-28T17:03:04Z","abstract_excerpt":"Typical multi-task learning (MTL) methods rely on architectural adjustments and a large trainable parameter set to jointly optimize over several tasks. However, when the number of tasks increases so do the complexity of the architectural adjustments and resource requirements. In this paper, we introduce a method which applies a conditional feature-wise transformation over the convolutional activations that enables a model to successfully perform a large number of tasks. To distinguish from regular MTL, we introduce Many Task Learning (MaTL) as a special case of MTL where more than 20 tasks are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12117","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":""},"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":"1903.12117","created_at":"2026-05-17T23:49:58.000888+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.12117v1","created_at":"2026-05-17T23:49:58.000888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12117","created_at":"2026-05-17T23:49:58.000888+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUS7L4G4HKYG","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUS7L4G4HKYGRQFC","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUS7L4G4","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM","json":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM.json","graph_json":"https://pith.science/api/pith-number/AUS7L4G4HKYGRQFCN7IKIT4YBM/graph.json","events_json":"https://pith.science/api/pith-number/AUS7L4G4HKYGRQFCN7IKIT4YBM/events.json","paper":"https://pith.science/paper/AUS7L4G4"},"agent_actions":{"view_html":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM","download_json":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM.json","view_paper":"https://pith.science/paper/AUS7L4G4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.12117&json=true","fetch_graph":"https://pith.science/api/pith-number/AUS7L4G4HKYGRQFCN7IKIT4YBM/graph.json","fetch_events":"https://pith.science/api/pith-number/AUS7L4G4HKYGRQFCN7IKIT4YBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM/action/storage_attestation","attest_author":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM/action/author_attestation","sign_citation":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM/action/citation_signature","submit_replication":"https://pith.science/pith/AUS7L4G4HKYGRQFCN7IKIT4YBM/action/replication_record"}},"created_at":"2026-05-17T23:49:58.000888+00:00","updated_at":"2026-05-17T23:49:58.000888+00:00"}