{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NPS6PYIM54I5T77MADPG6KDV32","short_pith_number":"pith:NPS6PYIM","schema_version":"1.0","canonical_sha256":"6be5e7e10cef11d9ffec00de6f2875debd7dad3f37d9af9613cb0802756fa296","source":{"kind":"arxiv","id":"1712.00559","version":3},"attestation_state":"computed","paper":{"title":"Progressive Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Barret Zoph, Chenxi Liu, Jonathan Huang, Jonathon Shlens, Kevin Murphy, Li Fei-Fei, Li-Jia Li, Maxim Neumann, Wei Hua","submitted_at":"2017-12-02T06:23:16Z","abstract_excerpt":"We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of "},"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":"1712.00559","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-02T06:23:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ca2f110814e14a89f100aedace9b712169308b76cefd22cdb2350a7685620fcc","abstract_canon_sha256":"516b105ac66093bef5a32ac2f45905d4d7c952b4980a160cee1cec0c5e698459"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.932213Z","signature_b64":"muJF64XdPp3BBpSucZ3m7hwo58vdv1IUzrLilvka2djf+UIZdnC//UTZUw9TBRozWTQ+xXFtnkWw27X/LkgZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be5e7e10cef11d9ffec00de6f2875debd7dad3f37d9af9613cb0802756fa296","last_reissued_at":"2026-05-18T00:09:41.931712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.931712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Barret Zoph, Chenxi Liu, Jonathan Huang, Jonathon Shlens, Kevin Murphy, Li Fei-Fei, Li-Jia Li, Maxim Neumann, Wei Hua","submitted_at":"2017-12-02T06:23:16Z","abstract_excerpt":"We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00559","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":"1712.00559","created_at":"2026-05-18T00:09:41.931781+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00559v3","created_at":"2026-05-18T00:09:41.931781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00559","created_at":"2026-05-18T00:09:41.931781+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPS6PYIM54I5","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPS6PYIM54I5T77M","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPS6PYIM","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11849","citing_title":"Genetic Deep Learning for Lung Cancer Screening","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32","json":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32.json","graph_json":"https://pith.science/api/pith-number/NPS6PYIM54I5T77MADPG6KDV32/graph.json","events_json":"https://pith.science/api/pith-number/NPS6PYIM54I5T77MADPG6KDV32/events.json","paper":"https://pith.science/paper/NPS6PYIM"},"agent_actions":{"view_html":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32","download_json":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32.json","view_paper":"https://pith.science/paper/NPS6PYIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00559&json=true","fetch_graph":"https://pith.science/api/pith-number/NPS6PYIM54I5T77MADPG6KDV32/graph.json","fetch_events":"https://pith.science/api/pith-number/NPS6PYIM54I5T77MADPG6KDV32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32/action/storage_attestation","attest_author":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32/action/author_attestation","sign_citation":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32/action/citation_signature","submit_replication":"https://pith.science/pith/NPS6PYIM54I5T77MADPG6KDV32/action/replication_record"}},"created_at":"2026-05-18T00:09:41.931781+00:00","updated_at":"2026-05-18T00:09:41.931781+00:00"}