{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GTAF4677LLCR67IQ7ICCGPDPKD","short_pith_number":"pith:GTAF4677","schema_version":"1.0","canonical_sha256":"34c05e7bff5ac51f7d10fa04233c6f50d0442b3feb81f3aa8e28cc2594c8631c","source":{"kind":"arxiv","id":"1807.06906","version":1},"attestation_state":"computed","paper":{"title":"Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Arber Zela, Frank Hutter, Stefan Falkner","submitted_at":"2018-07-18T13:11:08Z","abstract_excerpt":"While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimi"},"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":"1807.06906","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:11:08Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"1403d91b081f7db96e7a819cb46c0643b699059b512d7f93a965c06ef7c4dbc6","abstract_canon_sha256":"a53fc6c8c26fb46da5093f46e97a91d126c7f8df36d90db7756a612d442bf740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:25.370825Z","signature_b64":"XTVbDuTShSIauJlC9Yr4l3LWgEbiH5HDlCLhdE8I+BTT3j1NhlyY8uLtxkUgItwImbo0CcdYdn4jrL58oOVZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c05e7bff5ac51f7d10fa04233c6f50d0442b3feb81f3aa8e28cc2594c8631c","last_reissued_at":"2026-05-18T00:10:25.370150Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:25.370150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Klein, Arber Zela, Frank Hutter, Stefan Falkner","submitted_at":"2018-07-18T13:11:08Z","abstract_excerpt":"While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06906","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":""},"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":"1807.06906","created_at":"2026-05-18T00:10:25.370279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06906v1","created_at":"2026-05-18T00:10:25.370279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06906","created_at":"2026-05-18T00:10:25.370279+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTAF4677LLCR","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTAF4677LLCR67IQ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTAF4677","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":165,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":220,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD","json":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD.json","graph_json":"https://pith.science/api/pith-number/GTAF4677LLCR67IQ7ICCGPDPKD/graph.json","events_json":"https://pith.science/api/pith-number/GTAF4677LLCR67IQ7ICCGPDPKD/events.json","paper":"https://pith.science/paper/GTAF4677"},"agent_actions":{"view_html":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD","download_json":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD.json","view_paper":"https://pith.science/paper/GTAF4677","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06906&json=true","fetch_graph":"https://pith.science/api/pith-number/GTAF4677LLCR67IQ7ICCGPDPKD/graph.json","fetch_events":"https://pith.science/api/pith-number/GTAF4677LLCR67IQ7ICCGPDPKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD/action/storage_attestation","attest_author":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD/action/author_attestation","sign_citation":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD/action/citation_signature","submit_replication":"https://pith.science/pith/GTAF4677LLCR67IQ7ICCGPDPKD/action/replication_record"}},"created_at":"2026-05-18T00:10:25.370279+00:00","updated_at":"2026-05-18T00:10:25.370279+00:00"}