{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q23FIDC5DBJUCFBT3KBM4K7YEG","short_pith_number":"pith:Q23FIDC5","schema_version":"1.0","canonical_sha256":"86b6540c5d1853411433da82ce2bf8218afbf700d8e8685e5058d71f919a4586","source":{"kind":"arxiv","id":"1906.05721","version":1},"attestation_state":"computed","paper":{"title":"Visual Wake Words Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aakanksha Chowdhery, Andrew Howard, Jonathon Shlens, Pete Warden, Rocky Rhodes","submitted_at":"2019-06-12T17:47:21Z","abstract_excerpt":"The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT applications using machine learning at scale, but have extremely limited on-chip memory and compute capability. To deploy computer vision on such devices, we need tiny vision models that fit within a few hundred kilobytes of memory footprint in terms of peak usage and model size on device storage. To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a com"},"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":"1906.05721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-12T17:47:21Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"b6e702acc9e9a4b284ede7c578ab92798fbc28add7d650cd215dcc067364e310","abstract_canon_sha256":"eaa0f8b1643485c70421fae79cd35ec6197e78937915fa1e67e2fd7fdc6368f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:24.493712Z","signature_b64":"Y69F1pkVF0wNxSHJvFIlVJg4kc1xsvfizlxGHGbcHNsPdnsBSKrxG58gz3bZxroOy03HJm8XxnAt1PhNRVkqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b6540c5d1853411433da82ce2bf8218afbf700d8e8685e5058d71f919a4586","last_reissued_at":"2026-05-17T23:43:24.493234Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:24.493234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Wake Words Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aakanksha Chowdhery, Andrew Howard, Jonathon Shlens, Pete Warden, Rocky Rhodes","submitted_at":"2019-06-12T17:47:21Z","abstract_excerpt":"The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT applications using machine learning at scale, but have extremely limited on-chip memory and compute capability. To deploy computer vision on such devices, we need tiny vision models that fit within a few hundred kilobytes of memory footprint in terms of peak usage and model size on device storage. To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05721","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":"1906.05721","created_at":"2026-05-17T23:43:24.493300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05721v1","created_at":"2026-05-17T23:43:24.493300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05721","created_at":"2026-05-17T23:43:24.493300+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q23FIDC5DBJU","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q23FIDC5DBJUCFBT","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q23FIDC5","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2405.00892","citing_title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG","json":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG.json","graph_json":"https://pith.science/api/pith-number/Q23FIDC5DBJUCFBT3KBM4K7YEG/graph.json","events_json":"https://pith.science/api/pith-number/Q23FIDC5DBJUCFBT3KBM4K7YEG/events.json","paper":"https://pith.science/paper/Q23FIDC5"},"agent_actions":{"view_html":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG","download_json":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG.json","view_paper":"https://pith.science/paper/Q23FIDC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05721&json=true","fetch_graph":"https://pith.science/api/pith-number/Q23FIDC5DBJUCFBT3KBM4K7YEG/graph.json","fetch_events":"https://pith.science/api/pith-number/Q23FIDC5DBJUCFBT3KBM4K7YEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG/action/storage_attestation","attest_author":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG/action/author_attestation","sign_citation":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG/action/citation_signature","submit_replication":"https://pith.science/pith/Q23FIDC5DBJUCFBT3KBM4K7YEG/action/replication_record"}},"created_at":"2026-05-17T23:43:24.493300+00:00","updated_at":"2026-05-17T23:43:24.493300+00:00"}