{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AITXZS7K6EME5KBYYPBNYEGA4N","short_pith_number":"pith:AITXZS7K","schema_version":"1.0","canonical_sha256":"02277ccbeaf1184ea838c3c2dc10c0e35dcf46e46263472a8d6473db9d913b0e","source":{"kind":"arxiv","id":"2201.02711","version":2},"attestation_state":"computed","paper":{"title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Ahmet Enis Cetin, Diaa Badawi, Hongyi Pan","submitted_at":"2022-01-07T23:52:41Z","abstract_excerpt":"Convolution has been the core operation of modern deep neural networks. It is well-known that convolutions can be implemented in the Fourier Transform domain. In this paper, we propose to use binary block Walsh-Hadamard transform (WHT) instead of the Fourier transform. We use WHT-based binary layers to replace some of the regular convolution layers in deep neural networks. We utilize both one-dimensional (1-D) and two-dimensional (2-D) binary WHTs in this paper. In both 1-D and 2-D layers, we compute the binary WHT of the input feature map and denoise the WHT domain coefficients using a nonlin"},"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":"2201.02711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T23:52:41Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"896c317fd627f82592c823a844dabe2f31e583a910c6d72260d2c03eb74ea33a","abstract_canon_sha256":"0230830e9aea3f4113b808b180ca0a23ff17babeda82efbfc8021af147eba675"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:15.996326Z","signature_b64":"0lJEkSD2Kt5VapmhQawx/0vLM/qxt6ygTiSDY6XJ/CSBvLvuLosxoaYh6LjtQ+UdRkNoO4mdpf38voFHVmd4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02277ccbeaf1184ea838c3c2dc10c0e35dcf46e46263472a8d6473db9d913b0e","last_reissued_at":"2026-07-05T03:52:15.995935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:15.995935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Ahmet Enis Cetin, Diaa Badawi, Hongyi Pan","submitted_at":"2022-01-07T23:52:41Z","abstract_excerpt":"Convolution has been the core operation of modern deep neural networks. It is well-known that convolutions can be implemented in the Fourier Transform domain. In this paper, we propose to use binary block Walsh-Hadamard transform (WHT) instead of the Fourier transform. We use WHT-based binary layers to replace some of the regular convolution layers in deep neural networks. We utilize both one-dimensional (1-D) and two-dimensional (2-D) binary WHTs in this paper. In both 1-D and 2-D layers, we compute the binary WHT of the input feature map and denoise the WHT domain coefficients using a nonlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02711","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.02711/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":"2201.02711","created_at":"2026-07-05T03:52:15.995993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02711v2","created_at":"2026-07-05T03:52:15.995993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02711","created_at":"2026-07-05T03:52:15.995993+00:00"},{"alias_kind":"pith_short_12","alias_value":"AITXZS7K6EME","created_at":"2026-07-05T03:52:15.995993+00:00"},{"alias_kind":"pith_short_16","alias_value":"AITXZS7K6EME5KBY","created_at":"2026-07-05T03:52:15.995993+00:00"},{"alias_kind":"pith_short_8","alias_value":"AITXZS7K","created_at":"2026-07-05T03:52:15.995993+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/AITXZS7K6EME5KBYYPBNYEGA4N","json":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N.json","graph_json":"https://pith.science/api/pith-number/AITXZS7K6EME5KBYYPBNYEGA4N/graph.json","events_json":"https://pith.science/api/pith-number/AITXZS7K6EME5KBYYPBNYEGA4N/events.json","paper":"https://pith.science/paper/AITXZS7K"},"agent_actions":{"view_html":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N","download_json":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N.json","view_paper":"https://pith.science/paper/AITXZS7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/AITXZS7K6EME5KBYYPBNYEGA4N/graph.json","fetch_events":"https://pith.science/api/pith-number/AITXZS7K6EME5KBYYPBNYEGA4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N/action/storage_attestation","attest_author":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N/action/author_attestation","sign_citation":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N/action/citation_signature","submit_replication":"https://pith.science/pith/AITXZS7K6EME5KBYYPBNYEGA4N/action/replication_record"}},"created_at":"2026-07-05T03:52:15.995993+00:00","updated_at":"2026-07-05T03:52:15.995993+00:00"}