{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OU2KPTOW6GL22AAEZBUWTOQD75","short_pith_number":"pith:OU2KPTOW","schema_version":"1.0","canonical_sha256":"7534a7cdd6f197ad0004c86969ba03ff65d775105966d7096d8516b7bfa1a9bf","source":{"kind":"arxiv","id":"1803.03745","version":2},"attestation_state":"computed","paper":{"title":"Evolutionary Architecture Search For Deep Multitask Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Elliot Meyerson, Jason Liang, Risto Miikkulainen","submitted_at":"2018-03-10T03:02:09Z","abstract_excerpt":"Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There are many ways to tie the tasks together, and the design choices matter. The size and complexity of this problem exceeds human design ability, making it a compelling domain for evolutionary optimization. Using the existing state of the art soft ordering architecture as the starting point, methods for evolving the modules of this architecture and for evolving the overall topolog"},"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":"1803.03745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-03-10T03:02:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc594ee19ccb2fd6f550bead4a23e5a10df42b86306285c5e102e94751dae9fd","abstract_canon_sha256":"723265093cb24696d6616f463f580a02aa1eaff126d1ca957df28e8206f77b7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:09.016748Z","signature_b64":"vh8GcqiqgqfTcS08UzvQqeG+hTzLRBY65PVS/P/PL406xYIi5NxJwAXgZp0uaI+EH2WmwzSJWhLotpZbQYe5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7534a7cdd6f197ad0004c86969ba03ff65d775105966d7096d8516b7bfa1a9bf","last_reissued_at":"2026-05-18T00:18:09.016301Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:09.016301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary Architecture Search For Deep Multitask Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Elliot Meyerson, Jason Liang, Risto Miikkulainen","submitted_at":"2018-03-10T03:02:09Z","abstract_excerpt":"Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There are many ways to tie the tasks together, and the design choices matter. The size and complexity of this problem exceeds human design ability, making it a compelling domain for evolutionary optimization. Using the existing state of the art soft ordering architecture as the starting point, methods for evolving the modules of this architecture and for evolving the overall topolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03745","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":""},"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":"1803.03745","created_at":"2026-05-18T00:18:09.016382+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03745v2","created_at":"2026-05-18T00:18:09.016382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03745","created_at":"2026-05-18T00:18:09.016382+00:00"},{"alias_kind":"pith_short_12","alias_value":"OU2KPTOW6GL2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OU2KPTOW6GL22AAE","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OU2KPTOW","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04339","citing_title":"Feature Partitioning for Efficient Multi-Task Architectures","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75","json":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75.json","graph_json":"https://pith.science/api/pith-number/OU2KPTOW6GL22AAEZBUWTOQD75/graph.json","events_json":"https://pith.science/api/pith-number/OU2KPTOW6GL22AAEZBUWTOQD75/events.json","paper":"https://pith.science/paper/OU2KPTOW"},"agent_actions":{"view_html":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75","download_json":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75.json","view_paper":"https://pith.science/paper/OU2KPTOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03745&json=true","fetch_graph":"https://pith.science/api/pith-number/OU2KPTOW6GL22AAEZBUWTOQD75/graph.json","fetch_events":"https://pith.science/api/pith-number/OU2KPTOW6GL22AAEZBUWTOQD75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75/action/storage_attestation","attest_author":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75/action/author_attestation","sign_citation":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75/action/citation_signature","submit_replication":"https://pith.science/pith/OU2KPTOW6GL22AAEZBUWTOQD75/action/replication_record"}},"created_at":"2026-05-18T00:18:09.016382+00:00","updated_at":"2026-05-18T00:18:09.016382+00:00"}