{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IQ5C3ZISX5GA3GONNIY4UREEE7","short_pith_number":"pith:IQ5C3ZIS","schema_version":"1.0","canonical_sha256":"443a2de512bf4c0d99cd6a31ca448427ce9f77e50da0e774b166f8cb6b35b97c","source":{"kind":"arxiv","id":"1912.00848","version":1},"attestation_state":"computed","paper":{"title":"Neural Predictor for Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Bender, Hai Li, Hanxiao Liu, Pieter-Jan Kindermans, Wei Wen, Yiran Chen","submitted_at":"2019-12-02T15:10:59Z","abstract_excerpt":"Neural Architecture Search methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conceptually much simpler. First we train N random architectures to generate N (architecture, validation accuracy) pairs and use them to train a regression model that predicts accuracy based on the architecture. Next, we use this regression model to predict the validation accuracies of a large number of random architectures. Finally, we train the top-K predicted architectures and deploy the model with the best validation "},"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":"1912.00848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T15:10:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c8b4904d9f3c84da86437d43d8dc9619a401fa3bd335492a4a4a9d1aa211170e","abstract_canon_sha256":"4840d6d00be67477ba00f2e1a999c4809922b278a99174939723cfaeff39426a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:17.353363Z","signature_b64":"ypnxOBlYY9OH6b/i+8lfMruSliSPyR0fSIUh0CsMeTBRjYrPrrl9nFsTQl6SNwjaL8x/mienp1+GBMSYu9UAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"443a2de512bf4c0d99cd6a31ca448427ce9f77e50da0e774b166f8cb6b35b97c","last_reissued_at":"2026-07-05T00:23:17.352986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:17.352986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Predictor for Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Bender, Hai Li, Hanxiao Liu, Pieter-Jan Kindermans, Wei Wen, Yiran Chen","submitted_at":"2019-12-02T15:10:59Z","abstract_excerpt":"Neural Architecture Search methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conceptually much simpler. First we train N random architectures to generate N (architecture, validation accuracy) pairs and use them to train a regression model that predicts accuracy based on the architecture. Next, we use this regression model to predict the validation accuracies of a large number of random architectures. Finally, we train the top-K predicted architectures and deploy the model with the best validation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00848","kind":"arxiv","version":1},"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/1912.00848/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":"1912.00848","created_at":"2026-07-05T00:23:17.353045+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00848v1","created_at":"2026-07-05T00:23:17.353045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00848","created_at":"2026-07-05T00:23:17.353045+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQ5C3ZISX5GA","created_at":"2026-07-05T00:23:17.353045+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQ5C3ZISX5GA3GON","created_at":"2026-07-05T00:23:17.353045+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQ5C3ZIS","created_at":"2026-07-05T00:23:17.353045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03553","citing_title":"Efficient Global Neural Architecture Search","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7","json":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7.json","graph_json":"https://pith.science/api/pith-number/IQ5C3ZISX5GA3GONNIY4UREEE7/graph.json","events_json":"https://pith.science/api/pith-number/IQ5C3ZISX5GA3GONNIY4UREEE7/events.json","paper":"https://pith.science/paper/IQ5C3ZIS"},"agent_actions":{"view_html":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7","download_json":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7.json","view_paper":"https://pith.science/paper/IQ5C3ZIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00848&json=true","fetch_graph":"https://pith.science/api/pith-number/IQ5C3ZISX5GA3GONNIY4UREEE7/graph.json","fetch_events":"https://pith.science/api/pith-number/IQ5C3ZISX5GA3GONNIY4UREEE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7/action/storage_attestation","attest_author":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7/action/author_attestation","sign_citation":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7/action/citation_signature","submit_replication":"https://pith.science/pith/IQ5C3ZISX5GA3GONNIY4UREEE7/action/replication_record"}},"created_at":"2026-07-05T00:23:17.353045+00:00","updated_at":"2026-07-05T00:23:17.353045+00:00"}