{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7LO65UMEUUWBYSRU7WX2RHXUSF","short_pith_number":"pith:7LO65UME","schema_version":"1.0","canonical_sha256":"faddeed184a52c1c4a34fdafa89ef491649e7b977365246d097359da19a2fa38","source":{"kind":"arxiv","id":"1705.08142","version":3},"attestation_state":"computed","paper":{"title":"Latent Multi-task Architecture Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Anders S{\\o}gaard, Isabelle Augenstein, Joachim Bingel, Sebastian Ruder","submitted_at":"2017-05-23T08:58:09Z","abstract_excerpt":"Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)--(c). We present exp"},"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":"1705.08142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-23T08:58:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"0045fdbdf1e85c99e911be316039470038d9271c29161f6f9466c44b5e9f1a7b","abstract_canon_sha256":"74c2dce32a3b44bff34d511ee72f5b02c02bea8c118571ba5b4686fac13c120c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:31.095174Z","signature_b64":"kir9mO1zGS1Tk8GwEFnLRqxUxbLNqXPIJjsc89boNHmrZLhygoG3C4H1/xfY6JCeC9QFpgopjluwWM+0vCFnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faddeed184a52c1c4a34fdafa89ef491649e7b977365246d097359da19a2fa38","last_reissued_at":"2026-05-18T00:00:31.094601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:31.094601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Multi-task Architecture Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Anders S{\\o}gaard, Isabelle Augenstein, Joachim Bingel, Sebastian Ruder","submitted_at":"2017-05-23T08:58:09Z","abstract_excerpt":"Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)--(c). We present exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08142","kind":"arxiv","version":3},"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":"1705.08142","created_at":"2026-05-18T00:00:31.094686+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08142v3","created_at":"2026-05-18T00:00:31.094686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08142","created_at":"2026-05-18T00:00:31.094686+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LO65UMEUUWB","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LO65UMEUUWBYSRU","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LO65UME","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09084","citing_title":"Joint Detection of Malicious Domains and Infected Clients","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1804.07461","citing_title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14805","citing_title":"From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF","json":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF.json","graph_json":"https://pith.science/api/pith-number/7LO65UMEUUWBYSRU7WX2RHXUSF/graph.json","events_json":"https://pith.science/api/pith-number/7LO65UMEUUWBYSRU7WX2RHXUSF/events.json","paper":"https://pith.science/paper/7LO65UME"},"agent_actions":{"view_html":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF","download_json":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF.json","view_paper":"https://pith.science/paper/7LO65UME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08142&json=true","fetch_graph":"https://pith.science/api/pith-number/7LO65UMEUUWBYSRU7WX2RHXUSF/graph.json","fetch_events":"https://pith.science/api/pith-number/7LO65UMEUUWBYSRU7WX2RHXUSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF/action/storage_attestation","attest_author":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF/action/author_attestation","sign_citation":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF/action/citation_signature","submit_replication":"https://pith.science/pith/7LO65UMEUUWBYSRU7WX2RHXUSF/action/replication_record"}},"created_at":"2026-05-18T00:00:31.094686+00:00","updated_at":"2026-05-18T00:00:31.094686+00:00"}