{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DSWQYR3NMVN4CAXC2LW63DTXTT","short_pith_number":"pith:DSWQYR3N","schema_version":"1.0","canonical_sha256":"1cad0c476d655bc102e2d2eded8e779ccf3f63069bbd357a4726355e64bb6897","source":{"kind":"arxiv","id":"2209.09106","version":1},"attestation_state":"computed","paper":{"title":"Low-Energy Convolutional Neural Networks (CNNs) using Hadamard Method","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Varun Mannam","submitted_at":"2022-09-06T21:36:57Z","abstract_excerpt":"The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition and detection. However, the convolutional layer in CNN consumes significant energy compared to the fully connected layers. To mitigate this problem, a new approach based on the Hadamard transformation as an alternative to the convolution operation is demonstrated using two fundamental datasets, MNIST and CIFAR10. The mathematical expression of the Hadamard m"},"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":"2209.09106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-06T21:36:57Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"bdfe6e99242525aac9bb4f8e4b6cd9b28000b891153213bdbf55ab4ae80e4caa","abstract_canon_sha256":"ba58c39e68864cc7079d6a5e17b95a1db27fc251e56362c6083b3b6cdbe25854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:49.599735Z","signature_b64":"fheGgCF1QLa+DI2011qfcBxYsTKIXQ+I/3Wwzv1iVnwXYqMPNzo7nhwuFgd8V9iI4fVRMSxG+lkGbOzRvF0oBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cad0c476d655bc102e2d2eded8e779ccf3f63069bbd357a4726355e64bb6897","last_reissued_at":"2026-07-05T04:58:49.599274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:49.599274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Energy Convolutional Neural Networks (CNNs) using Hadamard Method","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Varun Mannam","submitted_at":"2022-09-06T21:36:57Z","abstract_excerpt":"The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition and detection. However, the convolutional layer in CNN consumes significant energy compared to the fully connected layers. To mitigate this problem, a new approach based on the Hadamard transformation as an alternative to the convolution operation is demonstrated using two fundamental datasets, MNIST and CIFAR10. The mathematical expression of the Hadamard m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09106","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/2209.09106/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":"2209.09106","created_at":"2026-07-05T04:58:49.599341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09106v1","created_at":"2026-07-05T04:58:49.599341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09106","created_at":"2026-07-05T04:58:49.599341+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSWQYR3NMVN4","created_at":"2026-07-05T04:58:49.599341+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSWQYR3NMVN4CAXC","created_at":"2026-07-05T04:58:49.599341+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSWQYR3N","created_at":"2026-07-05T04:58:49.599341+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/DSWQYR3NMVN4CAXC2LW63DTXTT","json":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT.json","graph_json":"https://pith.science/api/pith-number/DSWQYR3NMVN4CAXC2LW63DTXTT/graph.json","events_json":"https://pith.science/api/pith-number/DSWQYR3NMVN4CAXC2LW63DTXTT/events.json","paper":"https://pith.science/paper/DSWQYR3N"},"agent_actions":{"view_html":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT","download_json":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT.json","view_paper":"https://pith.science/paper/DSWQYR3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09106&json=true","fetch_graph":"https://pith.science/api/pith-number/DSWQYR3NMVN4CAXC2LW63DTXTT/graph.json","fetch_events":"https://pith.science/api/pith-number/DSWQYR3NMVN4CAXC2LW63DTXTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT/action/storage_attestation","attest_author":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT/action/author_attestation","sign_citation":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT/action/citation_signature","submit_replication":"https://pith.science/pith/DSWQYR3NMVN4CAXC2LW63DTXTT/action/replication_record"}},"created_at":"2026-07-05T04:58:49.599341+00:00","updated_at":"2026-07-05T04:58:49.599341+00:00"}