{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OA25JOUIM472HJSG56JKSUH5PM","short_pith_number":"pith:OA25JOUI","schema_version":"1.0","canonical_sha256":"7035d4ba88673fa3a646ef92a950fd7b35260627acc1cbbfe08699624afb204e","source":{"kind":"arxiv","id":"1611.06473","version":2},"attestation_state":"computed","paper":{"title":"LCNN: Lookup-based Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Hessam Bagherinezhad, Mohammad Rastegari","submitted_at":"2016-11-20T05:50:57Z","abstract_excerpt":"Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary and a small set of linear combinations. The size of the dictionary naturally traces a spectrum of tra"},"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":"1611.06473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-20T05:50:57Z","cross_cats_sorted":[],"title_canon_sha256":"a908cf5e45d04be932fa43cc4c30eabba3f252048a096a3df54f1bc72ba42961","abstract_canon_sha256":"561b53bfa63fb19d1c08604db4b30759f7d6d110125f37edb892b2210fd442c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:30.384906Z","signature_b64":"UYB7BkpEd12kdjtTMADqjIb138lr1mL4CE1VwWZlTExb+r6Z99R8hZV7ygoOCBcPMcueM+a5K4ZGjxm38ZziBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7035d4ba88673fa3a646ef92a950fd7b35260627acc1cbbfe08699624afb204e","last_reissued_at":"2026-05-18T00:42:30.384288Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:30.384288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LCNN: Lookup-based Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Hessam Bagherinezhad, Mohammad Rastegari","submitted_at":"2016-11-20T05:50:57Z","abstract_excerpt":"Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary and a small set of linear combinations. The size of the dictionary naturally traces a spectrum of tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06473","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":"1611.06473","created_at":"2026-05-18T00:42:30.384398+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06473v2","created_at":"2026-05-18T00:42:30.384398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06473","created_at":"2026-05-18T00:42:30.384398+00:00"},{"alias_kind":"pith_short_12","alias_value":"OA25JOUIM472","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OA25JOUIM472HJSG","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OA25JOUI","created_at":"2026-05-18T12:30:36.002864+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/OA25JOUIM472HJSG56JKSUH5PM","json":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM.json","graph_json":"https://pith.science/api/pith-number/OA25JOUIM472HJSG56JKSUH5PM/graph.json","events_json":"https://pith.science/api/pith-number/OA25JOUIM472HJSG56JKSUH5PM/events.json","paper":"https://pith.science/paper/OA25JOUI"},"agent_actions":{"view_html":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM","download_json":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM.json","view_paper":"https://pith.science/paper/OA25JOUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06473&json=true","fetch_graph":"https://pith.science/api/pith-number/OA25JOUIM472HJSG56JKSUH5PM/graph.json","fetch_events":"https://pith.science/api/pith-number/OA25JOUIM472HJSG56JKSUH5PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM/action/storage_attestation","attest_author":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM/action/author_attestation","sign_citation":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM/action/citation_signature","submit_replication":"https://pith.science/pith/OA25JOUIM472HJSG56JKSUH5PM/action/replication_record"}},"created_at":"2026-05-18T00:42:30.384398+00:00","updated_at":"2026-05-18T00:42:30.384398+00:00"}