{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FN2YI3FYBF6PRI4EO3JMGXTBEW","short_pith_number":"pith:FN2YI3FY","schema_version":"1.0","canonical_sha256":"2b75846cb8097cf8a38476d2c35e612596ebed61457a2c6ce0b576fe123457a0","source":{"kind":"arxiv","id":"2306.09827","version":1},"attestation_state":"computed","paper":{"title":"Building Blocks for a Complex-Valued Transformer Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Florian Eilers, Xiaoyi Jiang","submitted_at":"2023-06-16T13:11:15Z","abstract_excerpt":"Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or remote sensing. Additionally the Fourier transform of signals is complex-valued and has numerous applications. We aim to make deep learning directly applicable to these complex-valued signals without using projections into $\\mathbb{R}^2$. Thus we add to the recent developments of complex-valued neural networks by presenting building blocks to transfer the tr"},"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":"2306.09827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-16T13:11:15Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"8e7eef0febd40cdfc702fa5b8bdb4cbc584c029bfe82555c65e6515ff163f664","abstract_canon_sha256":"efb47a3cd0ad4b5cbcdc17cb1f8695581d5cc44707eca815ceb57fb1c07f866f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:24.363355Z","signature_b64":"PfoAZBYubzQk3+U1YF97aqLqFV45sjzgkH6l562YIqVJ8nvxUBtILIALjGfcXOb8uUOslFgFWkpdVcbhOc32CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b75846cb8097cf8a38476d2c35e612596ebed61457a2c6ce0b576fe123457a0","last_reissued_at":"2026-07-05T06:21:24.362871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:24.362871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Blocks for a Complex-Valued Transformer Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Florian Eilers, Xiaoyi Jiang","submitted_at":"2023-06-16T13:11:15Z","abstract_excerpt":"Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or remote sensing. Additionally the Fourier transform of signals is complex-valued and has numerous applications. We aim to make deep learning directly applicable to these complex-valued signals without using projections into $\\mathbb{R}^2$. Thus we add to the recent developments of complex-valued neural networks by presenting building blocks to transfer the tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09827","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/2306.09827/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":"2306.09827","created_at":"2026-07-05T06:21:24.362927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09827v1","created_at":"2026-07-05T06:21:24.362927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09827","created_at":"2026-07-05T06:21:24.362927+00:00"},{"alias_kind":"pith_short_12","alias_value":"FN2YI3FYBF6P","created_at":"2026-07-05T06:21:24.362927+00:00"},{"alias_kind":"pith_short_16","alias_value":"FN2YI3FYBF6PRI4E","created_at":"2026-07-05T06:21:24.362927+00:00"},{"alias_kind":"pith_short_8","alias_value":"FN2YI3FY","created_at":"2026-07-05T06:21:24.362927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10123","citing_title":"Complex-Valued Phase-Coherent Transformer","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW","json":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW.json","graph_json":"https://pith.science/api/pith-number/FN2YI3FYBF6PRI4EO3JMGXTBEW/graph.json","events_json":"https://pith.science/api/pith-number/FN2YI3FYBF6PRI4EO3JMGXTBEW/events.json","paper":"https://pith.science/paper/FN2YI3FY"},"agent_actions":{"view_html":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW","download_json":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW.json","view_paper":"https://pith.science/paper/FN2YI3FY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09827&json=true","fetch_graph":"https://pith.science/api/pith-number/FN2YI3FYBF6PRI4EO3JMGXTBEW/graph.json","fetch_events":"https://pith.science/api/pith-number/FN2YI3FYBF6PRI4EO3JMGXTBEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW/action/storage_attestation","attest_author":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW/action/author_attestation","sign_citation":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW/action/citation_signature","submit_replication":"https://pith.science/pith/FN2YI3FYBF6PRI4EO3JMGXTBEW/action/replication_record"}},"created_at":"2026-07-05T06:21:24.362927+00:00","updated_at":"2026-07-05T06:21:24.362927+00:00"}