{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SDIA3B2TX2GEBJNTP3BO2VAWAH","short_pith_number":"pith:SDIA3B2T","schema_version":"1.0","canonical_sha256":"90d00d8753be8c40a5b37ec2ed541601fed417b47c423805748e112aa9fceb1a","source":{"kind":"arxiv","id":"1705.09792","version":4},"attestation_state":"computed","paper":{"title":"Deep Complex Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Chiheb Trabelsi, Christopher J Pal, Dmitriy Serdyuk, Jo\\~ao Felipe Santos, Negar Rostamzadeh, Olexa Bilaniuk, Sandeep Subramanian, Soroush Mehri, Ying Zhang, Yoshua Bengio","submitted_at":"2017-05-27T09:04:55Z","abstract_excerpt":"At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis suggests that complex numbers could have a richer representational capacity and could also facilitate noise-robust memory retrieval mechanisms. Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks require"},"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":"1705.09792","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-05-27T09:04:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cee5febfe45e309b25b4aadd06b38f46c5ba5bd7dca44b10324202eb4eae259","abstract_canon_sha256":"2ca65bf4aad2e8fd15596b4cc23e68d43c47261965e83edd554b212b198e0340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.842093Z","signature_b64":"dau+p+ZWmX5C/Nr4YSIKLBzmaqQlKIkQr8PAX90ac3HxU8fXtGV6N3K8LqLE6OMDt7xiDxwat9pGPD8/DHATDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90d00d8753be8c40a5b37ec2ed541601fed417b47c423805748e112aa9fceb1a","last_reissued_at":"2026-05-18T00:22:39.841691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.841691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Complex Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Chiheb Trabelsi, Christopher J Pal, Dmitriy Serdyuk, Jo\\~ao Felipe Santos, Negar Rostamzadeh, Olexa Bilaniuk, Sandeep Subramanian, Soroush Mehri, Ying Zhang, Yoshua Bengio","submitted_at":"2017-05-27T09:04:55Z","abstract_excerpt":"At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis suggests that complex numbers could have a richer representational capacity and could also facilitate noise-robust memory retrieval mechanisms. Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks require"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09792","kind":"arxiv","version":4},"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":"1705.09792","created_at":"2026-05-18T00:22:39.841764+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09792v4","created_at":"2026-05-18T00:22:39.841764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09792","created_at":"2026-05-18T00:22:39.841764+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDIA3B2TX2GE","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDIA3B2TX2GEBJNT","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDIA3B2T","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2601.04775","citing_title":"Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13370","citing_title":"Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10123","citing_title":"Complex-Valued Phase-Coherent Transformer","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01726","citing_title":"FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14229","citing_title":"Magnitude Is All You Need? Rethinking Phase in Quantum Encoding of Complex SAR Data","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19993","citing_title":"Algorithm and Hardware Co-Design for Efficient Complex-Valued Uncertainty Estimation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH","json":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH.json","graph_json":"https://pith.science/api/pith-number/SDIA3B2TX2GEBJNTP3BO2VAWAH/graph.json","events_json":"https://pith.science/api/pith-number/SDIA3B2TX2GEBJNTP3BO2VAWAH/events.json","paper":"https://pith.science/paper/SDIA3B2T"},"agent_actions":{"view_html":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH","download_json":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH.json","view_paper":"https://pith.science/paper/SDIA3B2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09792&json=true","fetch_graph":"https://pith.science/api/pith-number/SDIA3B2TX2GEBJNTP3BO2VAWAH/graph.json","fetch_events":"https://pith.science/api/pith-number/SDIA3B2TX2GEBJNTP3BO2VAWAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH/action/storage_attestation","attest_author":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH/action/author_attestation","sign_citation":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH/action/citation_signature","submit_replication":"https://pith.science/pith/SDIA3B2TX2GEBJNTP3BO2VAWAH/action/replication_record"}},"created_at":"2026-05-18T00:22:39.841764+00:00","updated_at":"2026-05-18T00:22:39.841764+00:00"}