{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BR2PIZOY46IYQR7XM2GUNH573U","short_pith_number":"pith:BR2PIZOY","schema_version":"1.0","canonical_sha256":"0c74f465d8e7918847f7668d469fbfdd27a369bf737f581e4bd7f14fd124566c","source":{"kind":"arxiv","id":"1811.09828","version":4},"attestation_state":"computed","paper":{"title":"Evolutionary-Neural Hybrid Agents for Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Gesmundo, Andrey Khorlin, Krzysztof Maziarz, Marin Georgiev, Mingxing Tan","submitted_at":"2018-11-24T13:00:47Z","abstract_excerpt":"Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a "},"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":"1811.09828","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-24T13:00:47Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b8665e813d0a3a374de0fb640569fa648210154bfffe92701d47ef611ef16df6","abstract_canon_sha256":"d2564dba17daac9f7320574beb6d694c83e5353c7d164ab0b4a458f48c313d80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:53.583907Z","signature_b64":"94uKaYexPobBfHTrE5fDw8z1b3UbQ+LeaIQhJN2SyeIf6txv7sM3pz3i1YUN5FgBnDoginmcvtL2AqOKihOHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c74f465d8e7918847f7668d469fbfdd27a369bf737f581e4bd7f14fd124566c","last_reissued_at":"2026-07-05T00:40:53.583520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:53.583520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary-Neural Hybrid Agents for Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Gesmundo, Andrey Khorlin, Krzysztof Maziarz, Marin Georgiev, Mingxing Tan","submitted_at":"2018-11-24T13:00:47Z","abstract_excerpt":"Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09828","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.09828/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1811.09828","created_at":"2026-07-05T00:40:53.583577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09828v4","created_at":"2026-07-05T00:40:53.583577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09828","created_at":"2026-07-05T00:40:53.583577+00:00"},{"alias_kind":"pith_short_12","alias_value":"BR2PIZOY46IY","created_at":"2026-07-05T00:40:53.583577+00:00"},{"alias_kind":"pith_short_16","alias_value":"BR2PIZOY46IYQR7X","created_at":"2026-07-05T00:40:53.583577+00:00"},{"alias_kind":"pith_short_8","alias_value":"BR2PIZOY","created_at":"2026-07-05T00:40:53.583577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":154,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U","json":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U.json","graph_json":"https://pith.science/api/pith-number/BR2PIZOY46IYQR7XM2GUNH573U/graph.json","events_json":"https://pith.science/api/pith-number/BR2PIZOY46IYQR7XM2GUNH573U/events.json","paper":"https://pith.science/paper/BR2PIZOY"},"agent_actions":{"view_html":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U","download_json":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U.json","view_paper":"https://pith.science/paper/BR2PIZOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09828&json=true","fetch_graph":"https://pith.science/api/pith-number/BR2PIZOY46IYQR7XM2GUNH573U/graph.json","fetch_events":"https://pith.science/api/pith-number/BR2PIZOY46IYQR7XM2GUNH573U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U/action/storage_attestation","attest_author":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U/action/author_attestation","sign_citation":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U/action/citation_signature","submit_replication":"https://pith.science/pith/BR2PIZOY46IYQR7XM2GUNH573U/action/replication_record"}},"created_at":"2026-07-05T00:40:53.583577+00:00","updated_at":"2026-07-05T00:40:53.583577+00:00"}