{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4PKPLOBKVIOASHGIWP2PJSFABM","short_pith_number":"pith:4PKPLOBK","schema_version":"1.0","canonical_sha256":"e3d4f5b82aaa1c091cc8b3f4f4c8a00b34657ff9b2a1dc58608e1b74cecad7df","source":{"kind":"arxiv","id":"1907.01791","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Networks With Universe, Group, and Task Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Markus Dreyer, Mengwen Liu, Shiva Pentyala","submitted_at":"2019-07-03T08:39:14Z","abstract_excerpt":"We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at differe"},"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":"1907.01791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-03T08:39:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"760eb61ecaa58cb19827853f66fb865e0d511389366c21e71d21064f6f61d1a1","abstract_canon_sha256":"249cf77295e588229377aafd1b8b2639dd4616709ce5a31cec6ee3ee41efc020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:35.064653Z","signature_b64":"SD4tcXXRlpKAlsZ6Chxo0zDdWdNBFfMedojPW+6Q/3fptvDiDq1J9rZjqutmTYVIxwaLcnMYNLB2eCgOTu0mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3d4f5b82aaa1c091cc8b3f4f4c8a00b34657ff9b2a1dc58608e1b74cecad7df","last_reissued_at":"2026-05-17T23:41:35.063881Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:35.063881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Networks With Universe, Group, and Task Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Markus Dreyer, Mengwen Liu, Shiva Pentyala","submitted_at":"2019-07-03T08:39:14Z","abstract_excerpt":"We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01791","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":"1907.01791","created_at":"2026-05-17T23:41:35.064004+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01791v1","created_at":"2026-05-17T23:41:35.064004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01791","created_at":"2026-05-17T23:41:35.064004+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PKPLOBKVIOA","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PKPLOBKVIOASHGI","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PKPLOBK","created_at":"2026-05-18T12:33:10.108867+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/4PKPLOBKVIOASHGIWP2PJSFABM","json":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM.json","graph_json":"https://pith.science/api/pith-number/4PKPLOBKVIOASHGIWP2PJSFABM/graph.json","events_json":"https://pith.science/api/pith-number/4PKPLOBKVIOASHGIWP2PJSFABM/events.json","paper":"https://pith.science/paper/4PKPLOBK"},"agent_actions":{"view_html":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM","download_json":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM.json","view_paper":"https://pith.science/paper/4PKPLOBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01791&json=true","fetch_graph":"https://pith.science/api/pith-number/4PKPLOBKVIOASHGIWP2PJSFABM/graph.json","fetch_events":"https://pith.science/api/pith-number/4PKPLOBKVIOASHGIWP2PJSFABM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM/action/storage_attestation","attest_author":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM/action/author_attestation","sign_citation":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM/action/citation_signature","submit_replication":"https://pith.science/pith/4PKPLOBKVIOASHGIWP2PJSFABM/action/replication_record"}},"created_at":"2026-05-17T23:41:35.064004+00:00","updated_at":"2026-05-17T23:41:35.064004+00:00"}