{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7ZE537B24QK7KAYESW6NKSZNKQ","short_pith_number":"pith:7ZE537B2","schema_version":"1.0","canonical_sha256":"fe49ddfc3ae415f5030495bcd54b2d54368c910fc27920d84069ef86ede384b9","source":{"kind":"arxiv","id":"1711.00333","version":2},"attestation_state":"computed","paper":{"title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.OH","authors_text":"Jimmy Lin, Raphael Tang, Weijie Wang, Zhucheng Tu","submitted_at":"2017-10-30T18:24:35Z","abstract_excerpt":"Nearly all previous work on small-footprint keyword spotting with neural networks quantify model footprint in terms of the number of parameters and multiply operations for a feedforward inference pass. These values are, however, proxy measures since empirical performance in actual deployments is determined by many factors. In this paper, we study the power consumption of a family of convolutional neural networks for keyword spotting on a Raspberry Pi. We find that both proxies are good predictors of energy usage, although the number of multiplies is more predictive than the number of model par"},"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":"1711.00333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.OH","submitted_at":"2017-10-30T18:24:35Z","cross_cats_sorted":[],"title_canon_sha256":"2bc31e275e57d9cff5715b22ef968258921e7d2124d2efc2dc05ac91c3dca749","abstract_canon_sha256":"3ad3d14ae5ebd5b8398184f58b8d743a61f761afab2526f870d64630a1cbb9c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:14.491303Z","signature_b64":"3WRgml2JgbigMtcL2QxoQQ7M/TqcY5VpNI3Qw+3HhRRjP/OkQ8nFP4zkw8+ooOx1adMkB9DGRuUPjesZF1IjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe49ddfc3ae415f5030495bcd54b2d54368c910fc27920d84069ef86ede384b9","last_reissued_at":"2026-05-18T00:05:14.490746Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:14.490746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.OH","authors_text":"Jimmy Lin, Raphael Tang, Weijie Wang, Zhucheng Tu","submitted_at":"2017-10-30T18:24:35Z","abstract_excerpt":"Nearly all previous work on small-footprint keyword spotting with neural networks quantify model footprint in terms of the number of parameters and multiply operations for a feedforward inference pass. These values are, however, proxy measures since empirical performance in actual deployments is determined by many factors. In this paper, we study the power consumption of a family of convolutional neural networks for keyword spotting on a Raspberry Pi. We find that both proxies are good predictors of energy usage, although the number of multiplies is more predictive than the number of model par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00333","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":"1711.00333","created_at":"2026-05-18T00:05:14.490848+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00333v2","created_at":"2026-05-18T00:05:14.490848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00333","created_at":"2026-05-18T00:05:14.490848+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZE537B24QK7","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZE537B24QK7KAYE","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZE537B2","created_at":"2026-05-18T12:31:05.417338+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/7ZE537B24QK7KAYESW6NKSZNKQ","json":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ.json","graph_json":"https://pith.science/api/pith-number/7ZE537B24QK7KAYESW6NKSZNKQ/graph.json","events_json":"https://pith.science/api/pith-number/7ZE537B24QK7KAYESW6NKSZNKQ/events.json","paper":"https://pith.science/paper/7ZE537B2"},"agent_actions":{"view_html":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ","download_json":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ.json","view_paper":"https://pith.science/paper/7ZE537B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00333&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZE537B24QK7KAYESW6NKSZNKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZE537B24QK7KAYESW6NKSZNKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ/action/storage_attestation","attest_author":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ/action/author_attestation","sign_citation":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ/action/citation_signature","submit_replication":"https://pith.science/pith/7ZE537B24QK7KAYESW6NKSZNKQ/action/replication_record"}},"created_at":"2026-05-18T00:05:14.490848+00:00","updated_at":"2026-05-18T00:05:14.490848+00:00"}