{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DSCHUXDHGVYW5RQYUIED3HIMPO","short_pith_number":"pith:DSCHUXDH","schema_version":"1.0","canonical_sha256":"1c847a5c6735716ec618a2083d9d0c7b800c15719de7329fdb31fcef5ab6ee9c","source":{"kind":"arxiv","id":"1711.07128","version":3},"attestation_state":"computed","paper":{"title":"Hello Edge: Keyword Spotting on Microcontrollers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE","eess.AS"],"primary_cat":"cs.SD","authors_text":"Liangzhen Lai, Naveen Suda, Vikas Chandra, Yundong Zhang","submitted_at":"2017-11-20T03:19:03Z","abstract_excerpt":"Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application has highly constrained power budget and typically runs on tiny microcontrollers with limited memory and compute capability. The design of neural network architecture for KWS must consider these constrai"},"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":"1711.07128","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-11-20T03:19:03Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","eess.AS"],"title_canon_sha256":"4b8ad8aa74a6f8522c71c6717b8bc262e01f45963c4a2de64c696d79203d12a4","abstract_canon_sha256":"4d0330c304b34bce9c5ef78c18e80dae7118c702bcfcf47607fbdfc5704fea85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:16.384254Z","signature_b64":"3znArxgcKawwfPnOQfX4fOD8CepGvF2sjKEWd7eUrHd/QnQnbNkDk8v5HO78/KiRxkaPdl8kg/ENNI/625CJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c847a5c6735716ec618a2083d9d0c7b800c15719de7329fdb31fcef5ab6ee9c","last_reissued_at":"2026-05-18T00:23:16.383514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:16.383514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hello Edge: Keyword Spotting on Microcontrollers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE","eess.AS"],"primary_cat":"cs.SD","authors_text":"Liangzhen Lai, Naveen Suda, Vikas Chandra, Yundong Zhang","submitted_at":"2017-11-20T03:19:03Z","abstract_excerpt":"Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application has highly constrained power budget and typically runs on tiny microcontrollers with limited memory and compute capability. The design of neural network architecture for KWS must consider these constrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07128","kind":"arxiv","version":3},"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":"1711.07128","created_at":"2026-05-18T00:23:16.383642+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07128v3","created_at":"2026-05-18T00:23:16.383642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07128","created_at":"2026-05-18T00:23:16.383642+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSCHUXDHGVYW","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSCHUXDHGVYW5RQY","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSCHUXDH","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.11804","citing_title":"Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07936","citing_title":"A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15216","citing_title":"Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15647","citing_title":"Perforated Neural Networks for Keyword Spotting","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"1806.00582","citing_title":"Federated Learning with Non-IID Data","ref_index":1,"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":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07936","citing_title":"A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO","json":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO.json","graph_json":"https://pith.science/api/pith-number/DSCHUXDHGVYW5RQYUIED3HIMPO/graph.json","events_json":"https://pith.science/api/pith-number/DSCHUXDHGVYW5RQYUIED3HIMPO/events.json","paper":"https://pith.science/paper/DSCHUXDH"},"agent_actions":{"view_html":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO","download_json":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO.json","view_paper":"https://pith.science/paper/DSCHUXDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07128&json=true","fetch_graph":"https://pith.science/api/pith-number/DSCHUXDHGVYW5RQYUIED3HIMPO/graph.json","fetch_events":"https://pith.science/api/pith-number/DSCHUXDHGVYW5RQYUIED3HIMPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO/action/storage_attestation","attest_author":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO/action/author_attestation","sign_citation":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO/action/citation_signature","submit_replication":"https://pith.science/pith/DSCHUXDHGVYW5RQYUIED3HIMPO/action/replication_record"}},"created_at":"2026-05-18T00:23:16.383642+00:00","updated_at":"2026-05-18T00:23:16.383642+00:00"}