{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4MCTRLTMA657OPPXRH2CGETBU","short_pith_number":"pith:R4MCTRLT","schema_version":"1.0","canonical_sha256":"8f1829c573603ddfb9efbc4fa118930d304d67f56e4627423714a4d23e123752","source":{"kind":"arxiv","id":"2406.02075","version":2},"attestation_state":"computed","paper":{"title":"ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Helin Gong, Huansheng Ning, Liming Chen, Qi Qiu, Tao Zhu","submitted_at":"2024-06-04T07:54:31Z","abstract_excerpt":"Limited by the complexity of basis function (B-spline) calculations, Kolmogorov-Arnold Networks (KAN) suffer from restricted parallel computing capability on GPUs. This paper proposes a novel ReLU-KAN implementation that inherits the core idea of KAN. By adopting ReLU (Rectified Linear Unit) and point-wise multiplication, we simplify the design of KAN's basis function and optimize the computation process for efficient CUDA computing. The proposed ReLU-KAN architecture can be readily implemented on existing deep learning frameworks (e.g., PyTorch) for both inference and training. Experimental r"},"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":"2406.02075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:54:31Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"e4bfb245148a06b25582d0ee5a833a96d605202e04036ed4172caa57dfcc9168","abstract_canon_sha256":"1dd8d4ac1f675c38a8844e480d6d5de6cfd7fba699b87dfd2f7155b39efa6df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:36.411911Z","signature_b64":"VJli5aPVXxFZH46wq7lFoqr7dfAc3sCkqIVzvlYYEylBimHpbVGIy6Cqow5SF/HdK+UHanxwWlpvPsBkxHFpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1829c573603ddfb9efbc4fa118930d304d67f56e4627423714a4d23e123752","last_reissued_at":"2026-07-05T08:54:36.411474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:36.411474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Helin Gong, Huansheng Ning, Liming Chen, Qi Qiu, Tao Zhu","submitted_at":"2024-06-04T07:54:31Z","abstract_excerpt":"Limited by the complexity of basis function (B-spline) calculations, Kolmogorov-Arnold Networks (KAN) suffer from restricted parallel computing capability on GPUs. This paper proposes a novel ReLU-KAN implementation that inherits the core idea of KAN. By adopting ReLU (Rectified Linear Unit) and point-wise multiplication, we simplify the design of KAN's basis function and optimize the computation process for efficient CUDA computing. The proposed ReLU-KAN architecture can be readily implemented on existing deep learning frameworks (e.g., PyTorch) for both inference and training. Experimental r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02075","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/2406.02075/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":"2406.02075","created_at":"2026-07-05T08:54:36.411530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02075v2","created_at":"2026-07-05T08:54:36.411530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02075","created_at":"2026-07-05T08:54:36.411530+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4MCTRLTMA65","created_at":"2026-07-05T08:54:36.411530+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4MCTRLTMA657OPP","created_at":"2026-07-05T08:54:36.411530+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4MCTRLT","created_at":"2026-07-05T08:54:36.411530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02598","citing_title":"Assessing Region-Level EEG Contributions to Cognitive Workload Prediction","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29688","citing_title":"A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2410.03801","citing_title":"P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19536","citing_title":"A Dual Physics-Informed Kolmogorov-Arnold Neural Network Framework for Continuum Topology Optimization","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23599","citing_title":"Partition-of-Unity Gaussian Kolmogorov-Arnold Networks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21174","citing_title":"Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU","json":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU.json","graph_json":"https://pith.science/api/pith-number/R4MCTRLTMA657OPPXRH2CGETBU/graph.json","events_json":"https://pith.science/api/pith-number/R4MCTRLTMA657OPPXRH2CGETBU/events.json","paper":"https://pith.science/paper/R4MCTRLT"},"agent_actions":{"view_html":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU","download_json":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU.json","view_paper":"https://pith.science/paper/R4MCTRLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02075&json=true","fetch_graph":"https://pith.science/api/pith-number/R4MCTRLTMA657OPPXRH2CGETBU/graph.json","fetch_events":"https://pith.science/api/pith-number/R4MCTRLTMA657OPPXRH2CGETBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU/action/storage_attestation","attest_author":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU/action/author_attestation","sign_citation":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU/action/citation_signature","submit_replication":"https://pith.science/pith/R4MCTRLTMA657OPPXRH2CGETBU/action/replication_record"}},"created_at":"2026-07-05T08:54:36.411530+00:00","updated_at":"2026-07-05T08:54:36.411530+00:00"}