{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4NK4IJ6SPIMRR457RDW4C63JJY","short_pith_number":"pith:4NK4IJ6S","schema_version":"1.0","canonical_sha256":"e355c427d27a1918f3bf88edc17b694e1273fddc4b162d78c8e9058d87f367b5","source":{"kind":"arxiv","id":"2211.04635","version":1},"attestation_state":"computed","paper":{"title":"LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.LG","authors_text":"Biqiao Zhang, Haichuan Yang, Ivaylo Enchev, Limin Tang, Li Wan, Ming Sun, Raghuraman Krishnamoorthi, Raziel Alvarez, Vikas Chandra, Xin Lei, Yangyang Shi, Yiteng Huang, Zhaojun Yang","submitted_at":"2022-11-09T01:52:17Z","abstract_excerpt":"This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units like microcontrollers. ML operators exhibit heterogeneous efficiency profiles on power-efficient hardware. Given the exact theoretical computation cost, int8 operators are more computation-effective than float operators, and linear layers are often more efficient than other layers. The proposed LiCo-Net is a dual-phase system that uses the efficient int8 linear operators at the inference phase and applies streaming con"},"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":"2211.04635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T01:52:17Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"fe16f639ad085408edc0218e0a5665489956308471b50003555b38b62e147f37","abstract_canon_sha256":"2490a46474a7dd2f558b3b46f09dd319efdd3d268694da564bb7c93d4eb2e14f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:40.237184Z","signature_b64":"1NWgqUAPbZeL5oY+vkaI+PKsXNVfKPeGq0iyagountRG3mPHQc1c6/EWXETfMnsNBokQAbyBMRkVBP28dWKPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e355c427d27a1918f3bf88edc17b694e1273fddc4b162d78c8e9058d87f367b5","last_reissued_at":"2026-07-05T05:14:40.236753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:40.236753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.LG","authors_text":"Biqiao Zhang, Haichuan Yang, Ivaylo Enchev, Limin Tang, Li Wan, Ming Sun, Raghuraman Krishnamoorthi, Raziel Alvarez, Vikas Chandra, Xin Lei, Yangyang Shi, Yiteng Huang, Zhaojun Yang","submitted_at":"2022-11-09T01:52:17Z","abstract_excerpt":"This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units like microcontrollers. ML operators exhibit heterogeneous efficiency profiles on power-efficient hardware. Given the exact theoretical computation cost, int8 operators are more computation-effective than float operators, and linear layers are often more efficient than other layers. The proposed LiCo-Net is a dual-phase system that uses the efficient int8 linear operators at the inference phase and applies streaming con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04635","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.04635/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2211.04635","created_at":"2026-07-05T05:14:40.236811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.04635v1","created_at":"2026-07-05T05:14:40.236811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04635","created_at":"2026-07-05T05:14:40.236811+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NK4IJ6SPIMR","created_at":"2026-07-05T05:14:40.236811+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NK4IJ6SPIMRR457","created_at":"2026-07-05T05:14:40.236811+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NK4IJ6S","created_at":"2026-07-05T05:14:40.236811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11169","citing_title":"Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY","json":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY.json","graph_json":"https://pith.science/api/pith-number/4NK4IJ6SPIMRR457RDW4C63JJY/graph.json","events_json":"https://pith.science/api/pith-number/4NK4IJ6SPIMRR457RDW4C63JJY/events.json","paper":"https://pith.science/paper/4NK4IJ6S"},"agent_actions":{"view_html":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY","download_json":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY.json","view_paper":"https://pith.science/paper/4NK4IJ6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.04635&json=true","fetch_graph":"https://pith.science/api/pith-number/4NK4IJ6SPIMRR457RDW4C63JJY/graph.json","fetch_events":"https://pith.science/api/pith-number/4NK4IJ6SPIMRR457RDW4C63JJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY/action/storage_attestation","attest_author":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY/action/author_attestation","sign_citation":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY/action/citation_signature","submit_replication":"https://pith.science/pith/4NK4IJ6SPIMRR457RDW4C63JJY/action/replication_record"}},"created_at":"2026-07-05T05:14:40.236811+00:00","updated_at":"2026-07-05T05:14:40.236811+00:00"}