{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DPX2L66UPBWESDNGQ5ZFM37VRM","short_pith_number":"pith:DPX2L66U","schema_version":"1.0","canonical_sha256":"1befa5fbd4786c490da68772566ff58b3565b5f0eb4dcb13f4e24732e1d0af9c","source":{"kind":"arxiv","id":"1712.07420","version":2},"attestation_state":"computed","paper":{"title":"Finding Competitive Network Architectures Within a Day Using UCT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Wistuba","submitted_at":"2017-12-20T11:24:50Z","abstract_excerpt":"The design of neural network architectures for a new data set is a laborious task which requires human deep learning expertise. In order to make deep learning available for a broader audience, automated methods for finding a neural network architecture are vital. Recently proposed methods can already achieve human expert level performances. However, these methods have run times of months or even years of GPU computing time, ignoring hardware constraints as faced by many researchers and companies. We propose the use of Monte Carlo planning in combination with two different UCT (upper confidence"},"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":"1712.07420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-20T11:24:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"6815fee541038c3cc0033c7d3d17d3fb9f3e99c2fbdf0e1c9b24a81d683e5b46","abstract_canon_sha256":"572cddd23e6d7d6b2be19b6297cbb42d80b7b52688414c524e8f75a14c6740de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:04.782922Z","signature_b64":"FatNltQmnBuBFHFzozrMgKZfmSwk1LE1sImpMGwaiX7XQX9Q9RKjokxmxaDhC4FF9h0t8YUVZxGRhPDTi9+HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1befa5fbd4786c490da68772566ff58b3565b5f0eb4dcb13f4e24732e1d0af9c","last_reissued_at":"2026-05-17T23:44:04.782526Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:04.782526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Competitive Network Architectures Within a Day Using UCT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Wistuba","submitted_at":"2017-12-20T11:24:50Z","abstract_excerpt":"The design of neural network architectures for a new data set is a laborious task which requires human deep learning expertise. In order to make deep learning available for a broader audience, automated methods for finding a neural network architecture are vital. Recently proposed methods can already achieve human expert level performances. However, these methods have run times of months or even years of GPU computing time, ignoring hardware constraints as faced by many researchers and companies. We propose the use of Monte Carlo planning in combination with two different UCT (upper confidence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07420","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":"1712.07420","created_at":"2026-05-17T23:44:04.782587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07420v2","created_at":"2026-05-17T23:44:04.782587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07420","created_at":"2026-05-17T23:44:04.782587+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPX2L66UPBWE","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPX2L66UPBWESDNG","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPX2L66U","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02400","citing_title":"Refining the Structure of Neural Networks Using Matrix Conditioning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM","json":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM.json","graph_json":"https://pith.science/api/pith-number/DPX2L66UPBWESDNGQ5ZFM37VRM/graph.json","events_json":"https://pith.science/api/pith-number/DPX2L66UPBWESDNGQ5ZFM37VRM/events.json","paper":"https://pith.science/paper/DPX2L66U"},"agent_actions":{"view_html":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM","download_json":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM.json","view_paper":"https://pith.science/paper/DPX2L66U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07420&json=true","fetch_graph":"https://pith.science/api/pith-number/DPX2L66UPBWESDNGQ5ZFM37VRM/graph.json","fetch_events":"https://pith.science/api/pith-number/DPX2L66UPBWESDNGQ5ZFM37VRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM/action/storage_attestation","attest_author":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM/action/author_attestation","sign_citation":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM/action/citation_signature","submit_replication":"https://pith.science/pith/DPX2L66UPBWESDNGQ5ZFM37VRM/action/replication_record"}},"created_at":"2026-05-17T23:44:04.782587+00:00","updated_at":"2026-05-17T23:44:04.782587+00:00"}