{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4O5CMFQBRTWGN7XKJAWM5EC5FC","short_pith_number":"pith:4O5CMFQB","schema_version":"1.0","canonical_sha256":"e3ba2616018cec66feea482cce905d288d6db785c9aa7978c5653c4e9a7e26c8","source":{"kind":"arxiv","id":"1707.07012","version":4},"attestation_state":"computed","paper":{"title":"Learning Transferable Architectures for Scalable Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Jonathon Shlens, Quoc V. Le, Vijay Vasudevan","submitted_at":"2017-07-21T18:10:26Z","abstract_excerpt":"Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building block on a small dataset and then transfer the block to a larger dataset. The key contribution of this work is the design of a new search space (the \"NASNet search space\") which enables transferability. In our experiments, we search for the best convolutional layer (or \"cell\") on t"},"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":"1707.07012","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:10:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"97a04089bef234437611f3262d8debcc47ca54e1fbe2cfe785472dd51d1ef34d","abstract_canon_sha256":"7f368cce1072ebc00101db87f0bbb1533fc6ed2edcef831c1279d1a14bbe7114"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:46.409489Z","signature_b64":"Q8JaRWHI50DA1w/X51g+A0NYzjG7gdcl+ApqPEexHv4JVp0yw9zOLa/DdiZPzqDVIayM6cTPFUBUhjLgArAtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ba2616018cec66feea482cce905d288d6db785c9aa7978c5653c4e9a7e26c8","last_reissued_at":"2026-05-18T00:18:46.408765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:46.408765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Transferable Architectures for Scalable Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Barret Zoph, Jonathon Shlens, Quoc V. Le, Vijay Vasudevan","submitted_at":"2017-07-21T18:10:26Z","abstract_excerpt":"Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building block on a small dataset and then transfer the block to a larger dataset. The key contribution of this work is the design of a new search space (the \"NASNet search space\") which enables transferability. In our experiments, we search for the best convolutional layer (or \"cell\") on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07012","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":""},"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":"1707.07012","created_at":"2026-05-18T00:18:46.408877+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07012v4","created_at":"2026-05-18T00:18:46.408877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07012","created_at":"2026-05-18T00:18:46.408877+00:00"},{"alias_kind":"pith_short_12","alias_value":"4O5CMFQBRTWG","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4O5CMFQBRTWGN7XK","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4O5CMFQB","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.08714","citing_title":"Clustering and Classification Networks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1906.08879","citing_title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12348","citing_title":"MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00274","citing_title":"NetTailor: Tuning the Architecture, Not Just the Weights","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2310.02540","citing_title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"1710.05941","citing_title":"Searching for Activation Functions","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC","json":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC.json","graph_json":"https://pith.science/api/pith-number/4O5CMFQBRTWGN7XKJAWM5EC5FC/graph.json","events_json":"https://pith.science/api/pith-number/4O5CMFQBRTWGN7XKJAWM5EC5FC/events.json","paper":"https://pith.science/paper/4O5CMFQB"},"agent_actions":{"view_html":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC","download_json":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC.json","view_paper":"https://pith.science/paper/4O5CMFQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07012&json=true","fetch_graph":"https://pith.science/api/pith-number/4O5CMFQBRTWGN7XKJAWM5EC5FC/graph.json","fetch_events":"https://pith.science/api/pith-number/4O5CMFQBRTWGN7XKJAWM5EC5FC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC/action/storage_attestation","attest_author":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC/action/author_attestation","sign_citation":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC/action/citation_signature","submit_replication":"https://pith.science/pith/4O5CMFQBRTWGN7XKJAWM5EC5FC/action/replication_record"}},"created_at":"2026-05-18T00:18:46.408877+00:00","updated_at":"2026-05-18T00:18:46.408877+00:00"}