{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MD2WYLBS56NXCS44RK3RT37OEK","short_pith_number":"pith:MD2WYLBS","schema_version":"1.0","canonical_sha256":"60f56c2c32ef9b714b9c8ab719efee229b5f50ddf7d5d710494af91a4bdb8913","source":{"kind":"arxiv","id":"2408.07314","version":3},"attestation_state":"computed","paper":{"title":"Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Dong, Liangwei Zheng, Weitong Chen","submitted_at":"2024-08-14T06:15:55Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series d"},"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":"2408.07314","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-14T06:15:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ac971427acd67f925ce1a73ce164504cd776e1821de0ccd66c1fd157616f770","abstract_canon_sha256":"db8335398842b51703362d75810b2db7381d035e1fd17618bd12737e806e0fad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:38.044335Z","signature_b64":"PrOciwATIpnvOlPvTUc/a/GpF4FgXsTxwqH/2/8sLvZaDBmqi258U7oV+Oms7xdxY3/oX2wQD8nOqdu9vQfBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f56c2c32ef9b714b9c8ab719efee229b5f50ddf7d5d710494af91a4bdb8913","last_reissued_at":"2026-07-05T09:05:38.043844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:38.043844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Dong, Liangwei Zheng, Weitong Chen","submitted_at":"2024-08-14T06:15:55Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07314","kind":"arxiv","version":3},"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/2408.07314/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":"2408.07314","created_at":"2026-07-05T09:05:38.043906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07314v3","created_at":"2026-07-05T09:05:38.043906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07314","created_at":"2026-07-05T09:05:38.043906+00:00"},{"alias_kind":"pith_short_12","alias_value":"MD2WYLBS56NX","created_at":"2026-07-05T09:05:38.043906+00:00"},{"alias_kind":"pith_short_16","alias_value":"MD2WYLBS56NXCS44","created_at":"2026-07-05T09:05:38.043906+00:00"},{"alias_kind":"pith_short_8","alias_value":"MD2WYLBS","created_at":"2026-07-05T09:05:38.043906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18131","citing_title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK","json":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK.json","graph_json":"https://pith.science/api/pith-number/MD2WYLBS56NXCS44RK3RT37OEK/graph.json","events_json":"https://pith.science/api/pith-number/MD2WYLBS56NXCS44RK3RT37OEK/events.json","paper":"https://pith.science/paper/MD2WYLBS"},"agent_actions":{"view_html":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK","download_json":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK.json","view_paper":"https://pith.science/paper/MD2WYLBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07314&json=true","fetch_graph":"https://pith.science/api/pith-number/MD2WYLBS56NXCS44RK3RT37OEK/graph.json","fetch_events":"https://pith.science/api/pith-number/MD2WYLBS56NXCS44RK3RT37OEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK/action/storage_attestation","attest_author":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK/action/author_attestation","sign_citation":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK/action/citation_signature","submit_replication":"https://pith.science/pith/MD2WYLBS56NXCS44RK3RT37OEK/action/replication_record"}},"created_at":"2026-07-05T09:05:38.043906+00:00","updated_at":"2026-07-05T09:05:38.043906+00:00"}