{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z46FOROOQG4C5XLWLK5BF3OARW","short_pith_number":"pith:Z46FOROO","schema_version":"1.0","canonical_sha256":"cf3c5745ce81b82edd765aba12edc08d9b7572a2da45f2351cd7d4c7ee9163cb","source":{"kind":"arxiv","id":"1902.08142","version":3},"attestation_state":"computed","paper":{"title":"Evaluating the Search Phase of Neural Architecture Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Sciuto, Claudiu Musat, Kaicheng Yu, Martin Jaggi, Mathieu Salzmann","submitted_at":"2019-02-21T17:11:56Z","abstract_excerpt":"Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely based on their results on the downstream task. While intuitive, this fails to explicitly evaluate the effectiveness of their search strategies. In this paper, we propose to evaluate the NAS search phase. To this end, we compare the quality of the solutions obtained by NAS search policies with that of random architecture selection. We find tha"},"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":"1902.08142","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-21T17:11:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d602b69e48528f9d84ff33494d5ce9d6667e4afbbe1d33f9a5b64ea34e8c55dc","abstract_canon_sha256":"c043eaa0d5b05f8eb2c1db28df924644012f8851e775342d2761ea0926c80fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:05.725840Z","signature_b64":"6fMvD7wb6ZN2L8PAwvmHEBunWc/f53N36rnut8uduZeBpjaJ8JQ1d+p1vmj482IF+Px/zWMdb9Ki84UpjBVOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3c5745ce81b82edd765aba12edc08d9b7572a2da45f2351cd7d4c7ee9163cb","last_reissued_at":"2026-07-05T00:21:05.725309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:05.725309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Search Phase of Neural Architecture Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Sciuto, Claudiu Musat, Kaicheng Yu, Martin Jaggi, Mathieu Salzmann","submitted_at":"2019-02-21T17:11:56Z","abstract_excerpt":"Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely based on their results on the downstream task. While intuitive, this fails to explicitly evaluate the effectiveness of their search strategies. In this paper, we propose to evaluate the NAS search phase. To this end, we compare the quality of the solutions obtained by NAS search policies with that of random architecture selection. We find tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08142","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/1902.08142/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":"1902.08142","created_at":"2026-07-05T00:21:05.725390+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08142v3","created_at":"2026-07-05T00:21:05.725390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08142","created_at":"2026-07-05T00:21:05.725390+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z46FOROOQG4C","created_at":"2026-07-05T00:21:05.725390+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z46FOROOQG4C5XLW","created_at":"2026-07-05T00:21:05.725390+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z46FOROO","created_at":"2026-07-05T00:21:05.725390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29119","citing_title":"Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06187","citing_title":"In-Context Black-Box Optimization with Unreliable Feedback","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW","json":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW.json","graph_json":"https://pith.science/api/pith-number/Z46FOROOQG4C5XLWLK5BF3OARW/graph.json","events_json":"https://pith.science/api/pith-number/Z46FOROOQG4C5XLWLK5BF3OARW/events.json","paper":"https://pith.science/paper/Z46FOROO"},"agent_actions":{"view_html":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW","download_json":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW.json","view_paper":"https://pith.science/paper/Z46FOROO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08142&json=true","fetch_graph":"https://pith.science/api/pith-number/Z46FOROOQG4C5XLWLK5BF3OARW/graph.json","fetch_events":"https://pith.science/api/pith-number/Z46FOROOQG4C5XLWLK5BF3OARW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW/action/storage_attestation","attest_author":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW/action/author_attestation","sign_citation":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW/action/citation_signature","submit_replication":"https://pith.science/pith/Z46FOROOQG4C5XLWLK5BF3OARW/action/replication_record"}},"created_at":"2026-07-05T00:21:05.725390+00:00","updated_at":"2026-07-05T00:21:05.725390+00:00"}