{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U3VLYVXONBJ3T5NKFUHMF6JWIU","short_pith_number":"pith:U3VLYVXO","schema_version":"1.0","canonical_sha256":"a6eabc56ee6853b9f5aa2d0ec2f93645017ba02bb5b27fe57e1e5e911fa92ea8","source":{"kind":"arxiv","id":"2303.06797","version":3},"attestation_state":"computed","paper":{"title":"Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Ahmet Enis Cetin, Emadeldeen Hamdan, Hongyi Pan, Salih Atici, Xin Zhu","submitted_at":"2023-03-13T01:07:32Z","abstract_excerpt":"In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such as the Discrete Cosine Transform (DCT), Hadamard transform (HT), and biorthogonal Block Wavelet Transform (BWT). Furthermore, by taking advantage of the convolution theorems, convolutional filtering operations are performed in the transform domain using element-wise multiplications. Trainable soft-thresholding layers, that remove noise in the transform domain"},"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":"2303.06797","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T01:07:32Z","cross_cats_sorted":["eess.IV","eess.SP"],"title_canon_sha256":"db5ca9b48b555a6f5ef9a7fdfdfe62e22c8991524e192e3c80f3ae18a286ed8d","abstract_canon_sha256":"d5ac2e572a65e0664645b93047d660e1716b3d6d56ffc49103dfd320e32078d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:54.763293Z","signature_b64":"APqBSrpHEN0KVNzo/SW9+0zukzHaWC8XFLhgX8Baxes8lboycQsD2rnrr5U9OMowbfF+D+UWCp1Dbih7xEy7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6eabc56ee6853b9f5aa2d0ec2f93645017ba02bb5b27fe57e1e5e911fa92ea8","last_reissued_at":"2026-07-05T08:10:54.762731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:54.762731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Ahmet Enis Cetin, Emadeldeen Hamdan, Hongyi Pan, Salih Atici, Xin Zhu","submitted_at":"2023-03-13T01:07:32Z","abstract_excerpt":"In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such as the Discrete Cosine Transform (DCT), Hadamard transform (HT), and biorthogonal Block Wavelet Transform (BWT). Furthermore, by taking advantage of the convolution theorems, convolutional filtering operations are performed in the transform domain using element-wise multiplications. Trainable soft-thresholding layers, that remove noise in the transform domain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06797","kind":"arxiv","version":3},"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/2303.06797/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":"2303.06797","created_at":"2026-07-05T08:10:54.762790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06797v3","created_at":"2026-07-05T08:10:54.762790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06797","created_at":"2026-07-05T08:10:54.762790+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3VLYVXONBJ3","created_at":"2026-07-05T08:10:54.762790+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3VLYVXONBJ3T5NK","created_at":"2026-07-05T08:10:54.762790+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3VLYVXO","created_at":"2026-07-05T08:10:54.762790+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/U3VLYVXONBJ3T5NKFUHMF6JWIU","json":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU.json","graph_json":"https://pith.science/api/pith-number/U3VLYVXONBJ3T5NKFUHMF6JWIU/graph.json","events_json":"https://pith.science/api/pith-number/U3VLYVXONBJ3T5NKFUHMF6JWIU/events.json","paper":"https://pith.science/paper/U3VLYVXO"},"agent_actions":{"view_html":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU","download_json":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU.json","view_paper":"https://pith.science/paper/U3VLYVXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06797&json=true","fetch_graph":"https://pith.science/api/pith-number/U3VLYVXONBJ3T5NKFUHMF6JWIU/graph.json","fetch_events":"https://pith.science/api/pith-number/U3VLYVXONBJ3T5NKFUHMF6JWIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU/action/storage_attestation","attest_author":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU/action/author_attestation","sign_citation":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU/action/citation_signature","submit_replication":"https://pith.science/pith/U3VLYVXONBJ3T5NKFUHMF6JWIU/action/replication_record"}},"created_at":"2026-07-05T08:10:54.762790+00:00","updated_at":"2026-07-05T08:10:54.762790+00:00"}