{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N73WDFS2RAJBZK33RVYIHSS5UO","short_pith_number":"pith:N73WDFS2","schema_version":"1.0","canonical_sha256":"6ff761965a88121cab7b8d7083ca5da3b11ec399e5a026e67a94d427044664b3","source":{"kind":"arxiv","id":"2302.08286","version":1},"attestation_state":"computed","paper":{"title":"Theory and Implementation of Complex-Valued Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengfang Ren, Christele Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez, Jose Agustin Barrachina","submitted_at":"2023-02-16T13:31:10Z","abstract_excerpt":"This work explains in detail the theory behind Complex-Valued Neural Network (CVNN), including Wirtinger calculus, complex backpropagation, and basic modules such as complex layers, complex activation functions, or complex weight initialization. We also show the impact of not adapting the weight initialization correctly to the complex domain. This work presents a strong focus on the implementation of such modules on Python using cvnn toolbox. We also perform simulations on real-valued data, casting to the complex domain by means of the Hilbert Transform, and verifying the potential interest of"},"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":"2302.08286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-16T13:31:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aff6daa4bf749d523ccadaecf614043ca4f73cbbbb62efdb3ac8eeeaf20aebc1","abstract_canon_sha256":"f36787f2fa5f01ca25ae646e57effd6e832456d2a100d97e46bb99255fa0a563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:36.460978Z","signature_b64":"murMjLGy1Lx6sOADqFnl//RGXVUPUpkTCMuhV3mhOTf/C3/XYFHP0BKChHG9i1McYtM2r/Wzcz7bPteJp5CBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ff761965a88121cab7b8d7083ca5da3b11ec399e5a026e67a94d427044664b3","last_reissued_at":"2026-07-05T05:42:36.460568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:36.460568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory and Implementation of Complex-Valued Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengfang Ren, Christele Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez, Jose Agustin Barrachina","submitted_at":"2023-02-16T13:31:10Z","abstract_excerpt":"This work explains in detail the theory behind Complex-Valued Neural Network (CVNN), including Wirtinger calculus, complex backpropagation, and basic modules such as complex layers, complex activation functions, or complex weight initialization. We also show the impact of not adapting the weight initialization correctly to the complex domain. This work presents a strong focus on the implementation of such modules on Python using cvnn toolbox. We also perform simulations on real-valued data, casting to the complex domain by means of the Hilbert Transform, and verifying the potential interest of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08286","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/2302.08286/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":"2302.08286","created_at":"2026-07-05T05:42:36.460631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08286v1","created_at":"2026-07-05T05:42:36.460631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08286","created_at":"2026-07-05T05:42:36.460631+00:00"},{"alias_kind":"pith_short_12","alias_value":"N73WDFS2RAJB","created_at":"2026-07-05T05:42:36.460631+00:00"},{"alias_kind":"pith_short_16","alias_value":"N73WDFS2RAJBZK33","created_at":"2026-07-05T05:42:36.460631+00:00"},{"alias_kind":"pith_short_8","alias_value":"N73WDFS2","created_at":"2026-07-05T05:42:36.460631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00467","citing_title":"Batch Normalization for Neural Networks on Complex Domains","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02385","citing_title":"Entanglement is Half the Story: Post-Selection vs. Partial Traces","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO","json":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO.json","graph_json":"https://pith.science/api/pith-number/N73WDFS2RAJBZK33RVYIHSS5UO/graph.json","events_json":"https://pith.science/api/pith-number/N73WDFS2RAJBZK33RVYIHSS5UO/events.json","paper":"https://pith.science/paper/N73WDFS2"},"agent_actions":{"view_html":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO","download_json":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO.json","view_paper":"https://pith.science/paper/N73WDFS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08286&json=true","fetch_graph":"https://pith.science/api/pith-number/N73WDFS2RAJBZK33RVYIHSS5UO/graph.json","fetch_events":"https://pith.science/api/pith-number/N73WDFS2RAJBZK33RVYIHSS5UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO/action/storage_attestation","attest_author":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO/action/author_attestation","sign_citation":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO/action/citation_signature","submit_replication":"https://pith.science/pith/N73WDFS2RAJBZK33RVYIHSS5UO/action/replication_record"}},"created_at":"2026-07-05T05:42:36.460631+00:00","updated_at":"2026-07-05T05:42:36.460631+00:00"}