{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BXHQ63LBQFAGPAUWQEBU3MK5PX","short_pith_number":"pith:BXHQ63LB","schema_version":"1.0","canonical_sha256":"0dcf0f6d61814067829681034db15d7dd4b705ea679c28f213fbee3acb18a9a2","source":{"kind":"arxiv","id":"1812.09926","version":3},"attestation_state":"computed","paper":{"title":"SNAS: Stochastic Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunxiao Liu, Hehui Zheng, Liang Lin, Sirui Xie","submitted_at":"2018-12-24T14:13:16Z","abstract_excerpt":"We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline. In this work, NAS is reformulated as an optimization problem on parameters of a joint distribution for the search space in a cell. To leverage the gradient information in generic differentiable loss for architecture search, a novel search gradient is proposed. We prove that this"},"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":"1812.09926","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-24T14:13:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6732ce62d356f6217f5cb6664979af9f5a7f104a633c67f7bec9e1fdd1a7452c","abstract_canon_sha256":"2ff505c2e572a7014486af351bec252a6a7cad5b27c8161d0cfd929a61f824db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:51.353631Z","signature_b64":"EjWIYQuT13lRoo2cV9bcdHh+zodmRl1WDumyrqlJQez5uF753mvCEuXJPrCzhd0Yc0ONmHAsPKBYA3WbIQp6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dcf0f6d61814067829681034db15d7dd4b705ea679c28f213fbee3acb18a9a2","last_reissued_at":"2026-07-05T00:51:51.353128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:51.353128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SNAS: Stochastic Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunxiao Liu, Hehui Zheng, Liang Lin, Sirui Xie","submitted_at":"2018-12-24T14:13:16Z","abstract_excerpt":"We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline. In this work, NAS is reformulated as an optimization problem on parameters of a joint distribution for the search space in a cell. To leverage the gradient information in generic differentiable loss for architecture search, a novel search gradient is proposed. We prove that this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09926","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.09926/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":"1812.09926","created_at":"2026-07-05T00:51:51.353186+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09926v3","created_at":"2026-07-05T00:51:51.353186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09926","created_at":"2026-07-05T00:51:51.353186+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXHQ63LBQFAG","created_at":"2026-07-05T00:51:51.353186+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXHQ63LBQFAGPAUW","created_at":"2026-07-05T00:51:51.353186+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXHQ63LB","created_at":"2026-07-05T00:51:51.353186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10989","citing_title":"SURGE: Surrogate Gradient Adaptation in Binary Neural Networks","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10989","citing_title":"SURGE: Surrogate Gradient Adaptation in Binary Neural Networks","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX","json":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX.json","graph_json":"https://pith.science/api/pith-number/BXHQ63LBQFAGPAUWQEBU3MK5PX/graph.json","events_json":"https://pith.science/api/pith-number/BXHQ63LBQFAGPAUWQEBU3MK5PX/events.json","paper":"https://pith.science/paper/BXHQ63LB"},"agent_actions":{"view_html":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX","download_json":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX.json","view_paper":"https://pith.science/paper/BXHQ63LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09926&json=true","fetch_graph":"https://pith.science/api/pith-number/BXHQ63LBQFAGPAUWQEBU3MK5PX/graph.json","fetch_events":"https://pith.science/api/pith-number/BXHQ63LBQFAGPAUWQEBU3MK5PX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX/action/storage_attestation","attest_author":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX/action/author_attestation","sign_citation":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX/action/citation_signature","submit_replication":"https://pith.science/pith/BXHQ63LBQFAGPAUWQEBU3MK5PX/action/replication_record"}},"created_at":"2026-07-05T00:51:51.353186+00:00","updated_at":"2026-07-05T00:51:51.353186+00:00"}