{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y5T47YOM5H4WLS4RJRZWER3JCL","short_pith_number":"pith:Y5T47YOM","schema_version":"1.0","canonical_sha256":"c767cfe1cce9f965cb914c7362476912e642abd965a2053f05130502d45844b2","source":{"kind":"arxiv","id":"2102.11535","version":4},"attestation_state":"computed","paper":{"title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wuyang Chen, Xinyu Gong, Zhangyang Wang","submitted_at":"2021-02-23T07:50:44Z","abstract_excerpt":"Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by proposing a novel framework called training-free neural architecture search (TE-NAS). TE-NAS ranks arc"},"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":"2102.11535","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:50:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f715e2822c462cb7b07dcd915e36f4cf8e8c4c0e23fed5bdac95bd401d9d404f","abstract_canon_sha256":"22e7ab2704fdc15db647d39df5c50b48b3b66563674cc4390a5879661a191431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:27.468259Z","signature_b64":"WJIzkRSwEOosleg4/XNRRiGdSZtFZsFWMY6WZefOc4TCkVRBACbrIDUhWqQsOacislUjEGlVik5jsQkmXlFUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c767cfe1cce9f965cb914c7362476912e642abd965a2053f05130502d45844b2","last_reissued_at":"2026-07-05T02:23:27.467745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:27.467745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wuyang Chen, Xinyu Gong, Zhangyang Wang","submitted_at":"2021-02-23T07:50:44Z","abstract_excerpt":"Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by proposing a novel framework called training-free neural architecture search (TE-NAS). TE-NAS ranks arc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11535","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/2102.11535/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":"2102.11535","created_at":"2026-07-05T02:23:27.467807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11535v4","created_at":"2026-07-05T02:23:27.467807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11535","created_at":"2026-07-05T02:23:27.467807+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5T47YOM5H4W","created_at":"2026-07-05T02:23:27.467807+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5T47YOM5H4WLS4R","created_at":"2026-07-05T02:23:27.467807+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5T47YOM","created_at":"2026-07-05T02:23:27.467807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29582","citing_title":"Bilevel Optimization for Neural Architecture Search","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10237","citing_title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL","json":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL.json","graph_json":"https://pith.science/api/pith-number/Y5T47YOM5H4WLS4RJRZWER3JCL/graph.json","events_json":"https://pith.science/api/pith-number/Y5T47YOM5H4WLS4RJRZWER3JCL/events.json","paper":"https://pith.science/paper/Y5T47YOM"},"agent_actions":{"view_html":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL","download_json":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL.json","view_paper":"https://pith.science/paper/Y5T47YOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11535&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5T47YOM5H4WLS4RJRZWER3JCL/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5T47YOM5H4WLS4RJRZWER3JCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL/action/storage_attestation","attest_author":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL/action/author_attestation","sign_citation":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL/action/citation_signature","submit_replication":"https://pith.science/pith/Y5T47YOM5H4WLS4RJRZWER3JCL/action/replication_record"}},"created_at":"2026-07-05T02:23:27.467807+00:00","updated_at":"2026-07-05T02:23:27.467807+00:00"}