{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4YEWB5L53FMAKNGIXPMKZCB54C","short_pith_number":"pith:4YEWB5L5","schema_version":"1.0","canonical_sha256":"e60960f57dd9580534c8bbd8ac883de0aeb354e6819e75566f34858ba59222e2","source":{"kind":"arxiv","id":"1801.06601","version":1},"attestation_state":"computed","paper":{"title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MS"],"primary_cat":"cs.NE","authors_text":"Liangzhen Lai, Naveen Suda, Vikas Chandra","submitted_at":"2018-01-19T23:39:15Z","abstract_excerpt":"Deep Neural Networks are becoming increasingly popular in always-on IoT edge devices performing data analytics right at the source, reducing latency as well as energy consumption for data communication. This paper presents CMSIS-NN, efficient kernels developed to maximize the performance and minimize the memory footprint of neural network (NN) applications on Arm Cortex-M processors targeted for intelligent IoT edge devices. Neural network inference based on CMSIS-NN kernels achieves 4.6X improvement in runtime/throughput and 4.9X improvement in energy efficiency."},"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":"1801.06601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-01-19T23:39:15Z","cross_cats_sorted":["cs.LG","cs.MS"],"title_canon_sha256":"50f0ef2c78119097368e98117a05972afafe8ab996c944ce932c21630c5a3f10","abstract_canon_sha256":"97eca0635274d8534d061d1684800959f86b907144ae786789d80f1cbb939049"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:28.257792Z","signature_b64":"lnUQKxVYu0E2Vikq0iORG8vqrYxSGh+O3Sj0mDKmjaoQseQnkAIm3qrKpE/l1Whv/ccK+8eMEYzGBs0gQ8UHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e60960f57dd9580534c8bbd8ac883de0aeb354e6819e75566f34858ba59222e2","last_reissued_at":"2026-05-18T00:25:28.257040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:28.257040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MS"],"primary_cat":"cs.NE","authors_text":"Liangzhen Lai, Naveen Suda, Vikas Chandra","submitted_at":"2018-01-19T23:39:15Z","abstract_excerpt":"Deep Neural Networks are becoming increasingly popular in always-on IoT edge devices performing data analytics right at the source, reducing latency as well as energy consumption for data communication. This paper presents CMSIS-NN, efficient kernels developed to maximize the performance and minimize the memory footprint of neural network (NN) applications on Arm Cortex-M processors targeted for intelligent IoT edge devices. Neural network inference based on CMSIS-NN kernels achieves 4.6X improvement in runtime/throughput and 4.9X improvement in energy efficiency."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06601","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":"1801.06601","created_at":"2026-05-18T00:25:28.257168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.06601v1","created_at":"2026-05-18T00:25:28.257168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06601","created_at":"2026-05-18T00:25:28.257168+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YEWB5L53FMA","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YEWB5L53FMAKNGI","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YEWB5L5","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2602.06523","citing_title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20853","citing_title":"SEABAD: A Tropical Bird Activity Detection Dataset for Passive Acoustic Monitoring","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15694","citing_title":"Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18704","citing_title":"Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"1806.00582","citing_title":"Federated Learning with Non-IID Data","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06523","citing_title":"MicroBi-ConvLSTM: An Ultra-Lightweight Efficient Model for Human Activity Recognition on Resource Constrained Devices","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09565","citing_title":"AEG: A Baremetal Framework for AI Acceleration via Direct Hardware Access in Heterogeneous Accelerators","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27004","citing_title":"EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09357","citing_title":"Split CNN Inference on Networked Microcontrollers","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15714","citing_title":"Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16113","citing_title":"Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03039","citing_title":"Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C","json":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C.json","graph_json":"https://pith.science/api/pith-number/4YEWB5L53FMAKNGIXPMKZCB54C/graph.json","events_json":"https://pith.science/api/pith-number/4YEWB5L53FMAKNGIXPMKZCB54C/events.json","paper":"https://pith.science/paper/4YEWB5L5"},"agent_actions":{"view_html":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C","download_json":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C.json","view_paper":"https://pith.science/paper/4YEWB5L5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.06601&json=true","fetch_graph":"https://pith.science/api/pith-number/4YEWB5L53FMAKNGIXPMKZCB54C/graph.json","fetch_events":"https://pith.science/api/pith-number/4YEWB5L53FMAKNGIXPMKZCB54C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C/action/storage_attestation","attest_author":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C/action/author_attestation","sign_citation":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C/action/citation_signature","submit_replication":"https://pith.science/pith/4YEWB5L53FMAKNGIXPMKZCB54C/action/replication_record"}},"created_at":"2026-05-18T00:25:28.257168+00:00","updated_at":"2026-05-18T00:25:28.257168+00:00"}