{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CK22EP5GME4AHAAOVENAHXYJXZ","short_pith_number":"pith:CK22EP5G","schema_version":"1.0","canonical_sha256":"12b5a23fa6613803800ea91a03df09be43264472794375db189c55e4778ff17c","source":{"kind":"arxiv","id":"1506.02117","version":4},"attestation_state":"computed","paper":{"title":"Learning Multiple Tasks with Multilinear Relationship Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Mingsheng Long, Philip S. Yu, Zhangjie Cao","submitted_at":"2015-06-06T04:38:48Z","abstract_excerpt":"Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task learning is how to exploit the task relatedness underlying parameter tensors and improve feature transferability in the multiple task-specific layers. This paper presents Multilinear Relationship Networks (MRN) that discover the task relationships based on novel tensor normal priors over parameter tensors of multiple task-specific layers in deep convolutional netw"},"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":"1506.02117","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-06T04:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"d5c673e713aa3fe0ab8a3ecfc1644b48cf4908f244db51fb4deee12289ff6316","abstract_canon_sha256":"051d93d1f336d36fee5d809b0640a8aeb0d778658468388e065de9177516f773"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:22.833862Z","signature_b64":"IwtYBSFrgFDXOpmfsza6areR01W8zu2PQplwmGzesexGNFf9r0i/WXZZ0bAbIlXbj9RR9a0Q94ya6plhmAYEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12b5a23fa6613803800ea91a03df09be43264472794375db189c55e4778ff17c","last_reissued_at":"2026-05-18T00:31:22.833220Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:22.833220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multiple Tasks with Multilinear Relationship Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Mingsheng Long, Philip S. Yu, Zhangjie Cao","submitted_at":"2015-06-06T04:38:48Z","abstract_excerpt":"Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task learning is how to exploit the task relatedness underlying parameter tensors and improve feature transferability in the multiple task-specific layers. This paper presents Multilinear Relationship Networks (MRN) that discover the task relationships based on novel tensor normal priors over parameter tensors of multiple task-specific layers in deep convolutional netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02117","kind":"arxiv","version":4},"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":"1506.02117","created_at":"2026-05-18T00:31:22.833300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.02117v4","created_at":"2026-05-18T00:31:22.833300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02117","created_at":"2026-05-18T00:31:22.833300+00:00"},{"alias_kind":"pith_short_12","alias_value":"CK22EP5GME4A","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CK22EP5GME4AHAAO","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CK22EP5G","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1706.05098","citing_title":"An Overview of Multi-Task Learning in Deep Neural Networks","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ","json":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ.json","graph_json":"https://pith.science/api/pith-number/CK22EP5GME4AHAAOVENAHXYJXZ/graph.json","events_json":"https://pith.science/api/pith-number/CK22EP5GME4AHAAOVENAHXYJXZ/events.json","paper":"https://pith.science/paper/CK22EP5G"},"agent_actions":{"view_html":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ","download_json":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ.json","view_paper":"https://pith.science/paper/CK22EP5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.02117&json=true","fetch_graph":"https://pith.science/api/pith-number/CK22EP5GME4AHAAOVENAHXYJXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CK22EP5GME4AHAAOVENAHXYJXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ/action/storage_attestation","attest_author":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ/action/author_attestation","sign_citation":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ/action/citation_signature","submit_replication":"https://pith.science/pith/CK22EP5GME4AHAAOVENAHXYJXZ/action/replication_record"}},"created_at":"2026-05-18T00:31:22.833300+00:00","updated_at":"2026-05-18T00:31:22.833300+00:00"}