{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ELKKBKASSRBLXAMEOVZPVIM2LR","short_pith_number":"pith:ELKKBKAS","schema_version":"1.0","canonical_sha256":"22d4a0a8129442bb81847572faa19a5c78375cb04b222362c5faa4e0246bcd73","source":{"kind":"arxiv","id":"1612.06519","version":1},"attestation_state":"computed","paper":{"title":"Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Forrest Iandola","submitted_at":"2016-12-20T06:20:43Z","abstract_excerpt":"In recent years, the research community has discovered that deep neural networks (DNNs) and convolutional neural networks (CNNs) can yield higher accuracy than all previous solutions to a broad array of machine learning problems. To our knowledge, there is no single CNN/DNN architecture that solves all problems optimally. Instead, the \"right\" CNN/DNN architecture varies depending on the application at hand. CNN/DNNs comprise an enormous design space. Quantitatively, we find that a small region of the CNN design space contains 30 billion different CNN architectures.\n  In this dissertation, we d"},"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":"1612.06519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-20T06:20:43Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"6743c7c1ed3f7dcba4d02bdfee1f422afbf7873cf85a9eea8291da2d5d175420","abstract_canon_sha256":"42e224e9ef5cc9e2c6677b6dde9da6d14164df7d0ef5a8379e4330d775af7852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:25.544843Z","signature_b64":"DhHuOSuXbRUfPvmRV7yEvwAJiIZloVwGBRmTbLho91ON6Q6VSEjVIXhdh52RibeJL2q+i9qtHI0l/PPBXvOxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d4a0a8129442bb81847572faa19a5c78375cb04b222362c5faa4e0246bcd73","last_reissued_at":"2026-05-18T00:54:25.544087Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:25.544087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Forrest Iandola","submitted_at":"2016-12-20T06:20:43Z","abstract_excerpt":"In recent years, the research community has discovered that deep neural networks (DNNs) and convolutional neural networks (CNNs) can yield higher accuracy than all previous solutions to a broad array of machine learning problems. To our knowledge, there is no single CNN/DNN architecture that solves all problems optimally. Instead, the \"right\" CNN/DNN architecture varies depending on the application at hand. CNN/DNNs comprise an enormous design space. Quantitatively, we find that a small region of the CNN design space contains 30 billion different CNN architectures.\n  In this dissertation, we d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06519","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":"1612.06519","created_at":"2026-05-18T00:54:25.544225+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.06519v1","created_at":"2026-05-18T00:54:25.544225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06519","created_at":"2026-05-18T00:54:25.544225+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELKKBKASSRBL","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELKKBKASSRBLXAME","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELKKBKAS","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR","json":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR.json","graph_json":"https://pith.science/api/pith-number/ELKKBKASSRBLXAMEOVZPVIM2LR/graph.json","events_json":"https://pith.science/api/pith-number/ELKKBKASSRBLXAMEOVZPVIM2LR/events.json","paper":"https://pith.science/paper/ELKKBKAS"},"agent_actions":{"view_html":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR","download_json":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR.json","view_paper":"https://pith.science/paper/ELKKBKAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.06519&json=true","fetch_graph":"https://pith.science/api/pith-number/ELKKBKASSRBLXAMEOVZPVIM2LR/graph.json","fetch_events":"https://pith.science/api/pith-number/ELKKBKASSRBLXAMEOVZPVIM2LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR/action/storage_attestation","attest_author":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR/action/author_attestation","sign_citation":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR/action/citation_signature","submit_replication":"https://pith.science/pith/ELKKBKASSRBLXAMEOVZPVIM2LR/action/replication_record"}},"created_at":"2026-05-18T00:54:25.544225+00:00","updated_at":"2026-05-18T00:54:25.544225+00:00"}