{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYSJ5PUSFCCW3A7TF52DW5BLQU","short_pith_number":"pith:MYSJ5PUS","schema_version":"1.0","canonical_sha256":"66249ebe9228856d83f32f743b742b853c0312494052634203e3237a63adab34","source":{"kind":"arxiv","id":"2409.19221","version":2},"attestation_state":"computed","paper":{"title":"Cauchy activation function and XNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Hongkun Zhang, Xin Li, Zhihong Xia","submitted_at":"2024-09-28T03:25:33Z","abstract_excerpt":"We have developed a novel activation function, named the Cauchy Activation Function. This function is derived from the Cauchy Integral Theorem in complex analysis and is specifically tailored for problems requiring high precision. This innovation has led to the creation of a new class of neural networks, which we call (Comple)XNet, or simply XNet. We will demonstrate that XNet is particularly effective for high-dimensional challenges such as image classification and solving Partial Differential Equations (PDEs). Our evaluations show that XNet significantly outperforms established benchmarks li"},"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":"2409.19221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T03:25:33Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"d2e551625149e175274f9060891dc8480dfeeb59cb2e63042f37652337ccf4bf","abstract_canon_sha256":"9297a1f91a85b4d3e44d89a8895480a1a499bfc2c1e0cce6d2dc0cb85e8854d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:06.421348Z","signature_b64":"avXnRWJID8vxDzm0aSovmGW+q1uBA88OkF1a9hNdD5AA2y6xaaXEZRl7OhLXx3pDc5QkhFG6MwL3MwuPFguuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66249ebe9228856d83f32f743b742b853c0312494052634203e3237a63adab34","last_reissued_at":"2026-07-05T10:06:06.420819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:06.420819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cauchy activation function and XNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Hongkun Zhang, Xin Li, Zhihong Xia","submitted_at":"2024-09-28T03:25:33Z","abstract_excerpt":"We have developed a novel activation function, named the Cauchy Activation Function. This function is derived from the Cauchy Integral Theorem in complex analysis and is specifically tailored for problems requiring high precision. This innovation has led to the creation of a new class of neural networks, which we call (Comple)XNet, or simply XNet. We will demonstrate that XNet is particularly effective for high-dimensional challenges such as image classification and solving Partial Differential Equations (PDEs). Our evaluations show that XNet significantly outperforms established benchmarks li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19221","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/2409.19221/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":"2409.19221","created_at":"2026-07-05T10:06:06.420883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19221v2","created_at":"2026-07-05T10:06:06.420883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19221","created_at":"2026-07-05T10:06:06.420883+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYSJ5PUSFCCW","created_at":"2026-07-05T10:06:06.420883+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYSJ5PUSFCCW3A7T","created_at":"2026-07-05T10:06:06.420883+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYSJ5PUS","created_at":"2026-07-05T10:06:06.420883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.06238","citing_title":"XNet-Enhanced Deep BSDE Method and Numerical Analysis","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU","json":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU.json","graph_json":"https://pith.science/api/pith-number/MYSJ5PUSFCCW3A7TF52DW5BLQU/graph.json","events_json":"https://pith.science/api/pith-number/MYSJ5PUSFCCW3A7TF52DW5BLQU/events.json","paper":"https://pith.science/paper/MYSJ5PUS"},"agent_actions":{"view_html":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU","download_json":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU.json","view_paper":"https://pith.science/paper/MYSJ5PUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19221&json=true","fetch_graph":"https://pith.science/api/pith-number/MYSJ5PUSFCCW3A7TF52DW5BLQU/graph.json","fetch_events":"https://pith.science/api/pith-number/MYSJ5PUSFCCW3A7TF52DW5BLQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU/action/storage_attestation","attest_author":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU/action/author_attestation","sign_citation":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU/action/citation_signature","submit_replication":"https://pith.science/pith/MYSJ5PUSFCCW3A7TF52DW5BLQU/action/replication_record"}},"created_at":"2026-07-05T10:06:06.420883+00:00","updated_at":"2026-07-05T10:06:06.420883+00:00"}