{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LWS3VG74U4Z7PXOJ5ZKPGOSAK6","short_pith_number":"pith:LWS3VG74","schema_version":"1.0","canonical_sha256":"5da5ba9bfca733f7ddc9ee54f33a40578e91d4482d868ee1a70e4d4daba69f6e","source":{"kind":"arxiv","id":"2502.07176","version":2},"attestation_state":"computed","paper":{"title":"MatrixKAN: Parallelized Kolmogorov-Arnold Network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cale Coffman, Lizhong Chen","submitted_at":"2025-02-11T01:59:46Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) are a new class of neural network architecture representing a promising alternative to the Multilayer Perceptron (MLP), demonstrating improved expressiveness and interpretability. However, KANs suffer from slow training and inference speeds relative to MLPs due in part to the recursive nature of the underlying B-spline calculations. This issue is particularly apparent with respect to KANs utilizing high-degree B-splines, as the number of required non-parallelizable recursions is proportional to B-spline degree. We solve this issue by proposing MatrixKAN, a nove"},"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":"2502.07176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T01:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"a33050c979e9c8868274a963809733ba8cc270107c84cc2a37d4876a4d02afa6","abstract_canon_sha256":"915368cfdae05ea7951a6cf23e398abe3d75f53bc0086743b606e06e9b32d38b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:13.088427Z","signature_b64":"jaC21q8vRhu52XegOuE+72G7o4oNJAd+LOyE3tFV177/0mWBG7axC7bRSXo9zUqdtZr8QQ5FcX56iMRsn5tlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da5ba9bfca733f7ddc9ee54f33a40578e91d4482d868ee1a70e4d4daba69f6e","last_reissued_at":"2026-07-05T10:22:13.087865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:13.087865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatrixKAN: Parallelized Kolmogorov-Arnold Network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cale Coffman, Lizhong Chen","submitted_at":"2025-02-11T01:59:46Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) are a new class of neural network architecture representing a promising alternative to the Multilayer Perceptron (MLP), demonstrating improved expressiveness and interpretability. However, KANs suffer from slow training and inference speeds relative to MLPs due in part to the recursive nature of the underlying B-spline calculations. This issue is particularly apparent with respect to KANs utilizing high-degree B-splines, as the number of required non-parallelizable recursions is proportional to B-spline degree. We solve this issue by proposing MatrixKAN, a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07176","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/2502.07176/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":"2502.07176","created_at":"2026-07-05T10:22:13.087943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07176v2","created_at":"2026-07-05T10:22:13.087943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07176","created_at":"2026-07-05T10:22:13.087943+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWS3VG74U4Z7","created_at":"2026-07-05T10:22:13.087943+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWS3VG74U4Z7PXOJ","created_at":"2026-07-05T10:22:13.087943+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWS3VG74","created_at":"2026-07-05T10:22:13.087943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6","json":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6.json","graph_json":"https://pith.science/api/pith-number/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/graph.json","events_json":"https://pith.science/api/pith-number/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/events.json","paper":"https://pith.science/paper/LWS3VG74"},"agent_actions":{"view_html":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6","download_json":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6.json","view_paper":"https://pith.science/paper/LWS3VG74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07176&json=true","fetch_graph":"https://pith.science/api/pith-number/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/graph.json","fetch_events":"https://pith.science/api/pith-number/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/action/storage_attestation","attest_author":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/action/author_attestation","sign_citation":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/action/citation_signature","submit_replication":"https://pith.science/pith/LWS3VG74U4Z7PXOJ5ZKPGOSAK6/action/replication_record"}},"created_at":"2026-07-05T10:22:13.087943+00:00","updated_at":"2026-07-05T10:22:13.087943+00:00"}