{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRVSBEKBBLDYP42ZAFI2BQWS7G","short_pith_number":"pith:RRVSBEKB","schema_version":"1.0","canonical_sha256":"8c6b2091410ac787f3590151a0c2d2f985a601ec18707756e8b31054ec99568d","source":{"kind":"arxiv","id":"2408.07906","version":1},"attestation_state":"computed","paper":{"title":"KAN versus MLP on Irregular or Noisy Functions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Chen Zeng, Haoran Shen, Jiahui Wang, Qiao Wang","submitted_at":"2024-08-15T03:24:07Z","abstract_excerpt":"In this paper, we compare the performance of Kolmogorov-Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) networks on irregular or noisy functions. We control the number of parameters and the size of the training samples to ensure a fair comparison. For clarity, we categorize the functions into six types: regular functions, continuous functions with local non-differentiable points, functions with jump discontinuities, functions with singularities, functions with coherent oscillations, and noisy functions. Our experimental results indicate that KAN does not always perform best. For some ty"},"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":"2408.07906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T03:24:07Z","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA"],"title_canon_sha256":"748f56ce6c4095afb0c991849220426abcceca6e857f31eaa2ca9174f0d9ab54","abstract_canon_sha256":"16d2ecccf805765627467c7c3a76508affb8f808e997c0ea21f493f50a375b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:41.783556Z","signature_b64":"Z8g9/u8VVTKVrb+nV71SR7jv1IiQ4veFTX3D7Nfot1ii1m1PMWp5rnlMttuoIl5FKBBIstBNtnGZu/sgh32OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6b2091410ac787f3590151a0c2d2f985a601ec18707756e8b31054ec99568d","last_reissued_at":"2026-07-05T08:55:41.783078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:41.783078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAN versus MLP on Irregular or Noisy Functions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Chen Zeng, Haoran Shen, Jiahui Wang, Qiao Wang","submitted_at":"2024-08-15T03:24:07Z","abstract_excerpt":"In this paper, we compare the performance of Kolmogorov-Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) networks on irregular or noisy functions. We control the number of parameters and the size of the training samples to ensure a fair comparison. For clarity, we categorize the functions into six types: regular functions, continuous functions with local non-differentiable points, functions with jump discontinuities, functions with singularities, functions with coherent oscillations, and noisy functions. Our experimental results indicate that KAN does not always perform best. For some ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07906","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/2408.07906/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":"2408.07906","created_at":"2026-07-05T08:55:41.783139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07906v1","created_at":"2026-07-05T08:55:41.783139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07906","created_at":"2026-07-05T08:55:41.783139+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRVSBEKBBLDY","created_at":"2026-07-05T08:55:41.783139+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRVSBEKBBLDYP42Z","created_at":"2026-07-05T08:55:41.783139+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRVSBEKB","created_at":"2026-07-05T08:55:41.783139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23425","citing_title":"Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02967","citing_title":"AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G","json":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G.json","graph_json":"https://pith.science/api/pith-number/RRVSBEKBBLDYP42ZAFI2BQWS7G/graph.json","events_json":"https://pith.science/api/pith-number/RRVSBEKBBLDYP42ZAFI2BQWS7G/events.json","paper":"https://pith.science/paper/RRVSBEKB"},"agent_actions":{"view_html":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G","download_json":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G.json","view_paper":"https://pith.science/paper/RRVSBEKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07906&json=true","fetch_graph":"https://pith.science/api/pith-number/RRVSBEKBBLDYP42ZAFI2BQWS7G/graph.json","fetch_events":"https://pith.science/api/pith-number/RRVSBEKBBLDYP42ZAFI2BQWS7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G/action/storage_attestation","attest_author":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G/action/author_attestation","sign_citation":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G/action/citation_signature","submit_replication":"https://pith.science/pith/RRVSBEKBBLDYP42ZAFI2BQWS7G/action/replication_record"}},"created_at":"2026-07-05T08:55:41.783139+00:00","updated_at":"2026-07-05T08:55:41.783139+00:00"}