{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S6SD7MZEZERAMMURSOU6JNO3SA","short_pith_number":"pith:S6SD7MZE","schema_version":"1.0","canonical_sha256":"97a43fb324c92206329193a9e4b5db9024e26488352d21bf1a3385901b69803c","source":{"kind":"arxiv","id":"1902.09635","version":2},"attestation_state":"computed","paper":{"title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Chris Ying, Eric Christiansen, Esteban Real, Frank Hutter, Kevin Murphy","submitted_at":"2019-02-25T21:56:54Z","abstract_excerpt":"Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on C"},"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":"1902.09635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T21:56:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"156a9fd1137a737f41bc1b446695976ccf24eb91addc8d2c11f8a83a66c69edd","abstract_canon_sha256":"771bc5d1be34922bb1135bbe570629432e607e0331eea2918e7c804d179d8770"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:18.501828Z","signature_b64":"Hxh0JtXYIRts4I7sQdcvq4gSYewPIPTJoZSCmhN//CpMcRZrTiIm2Q0pU2aplsLo1kD5O29yD4OIq66B9MQqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a43fb324c92206329193a9e4b5db9024e26488352d21bf1a3385901b69803c","last_reissued_at":"2026-05-17T23:46:18.500993Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:18.500993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Chris Ying, Eric Christiansen, Esteban Real, Frank Hutter, Kevin Murphy","submitted_at":"2019-02-25T21:56:54Z","abstract_excerpt":"Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09635","kind":"arxiv","version":2},"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":"1902.09635","created_at":"2026-05-17T23:46:18.501134+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09635v2","created_at":"2026-05-17T23:46:18.501134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09635","created_at":"2026-05-17T23:46:18.501134+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6SD7MZEZERA","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6SD7MZEZERAMMUR","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6SD7MZE","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2310.02540","citing_title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA","json":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA.json","graph_json":"https://pith.science/api/pith-number/S6SD7MZEZERAMMURSOU6JNO3SA/graph.json","events_json":"https://pith.science/api/pith-number/S6SD7MZEZERAMMURSOU6JNO3SA/events.json","paper":"https://pith.science/paper/S6SD7MZE"},"agent_actions":{"view_html":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA","download_json":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA.json","view_paper":"https://pith.science/paper/S6SD7MZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09635&json=true","fetch_graph":"https://pith.science/api/pith-number/S6SD7MZEZERAMMURSOU6JNO3SA/graph.json","fetch_events":"https://pith.science/api/pith-number/S6SD7MZEZERAMMURSOU6JNO3SA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA/action/storage_attestation","attest_author":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA/action/author_attestation","sign_citation":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA/action/citation_signature","submit_replication":"https://pith.science/pith/S6SD7MZEZERAMMURSOU6JNO3SA/action/replication_record"}},"created_at":"2026-05-17T23:46:18.501134+00:00","updated_at":"2026-05-17T23:46:18.501134+00:00"}