{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GAS4HGNBRLVFUNTPDNZ4N7XO2F","short_pith_number":"pith:GAS4HGNB","schema_version":"1.0","canonical_sha256":"3025c399a18aea5a366f1b73c6feeed157f85204d858d3b8ec8063a2f4b5636d","source":{"kind":"arxiv","id":"2410.01803","version":2},"attestation_state":"computed","paper":{"title":"On the expressiveness and spectral bias of KANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan W. Siegel, Thomas Y. Hou, Yixuan Wang, Ziming Liu","submitted_at":"2024-10-02T17:57:38Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) \\cite{liu2024kan} were very recently proposed as a potential alternative to the prevalent architectural backbone of many deep learning models, the multi-layer perceptron (MLP). KANs have seen success in various tasks of AI for science, with their empirical efficiency and accuracy demostrated in function regression, PDE solving, and many more scientific problems.\n  In this article, we revisit the comparison of KANs and MLPs, with emphasis on a theoretical perspective. On the one hand, we compare the representation and approximation capabilities of KANs and MLPs."},"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":"2410.01803","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:57:38Z","cross_cats_sorted":[],"title_canon_sha256":"39a9e28fc8ec9bc2397153a0a906337f5ecc6c1cdc362544a7235266de02e67a","abstract_canon_sha256":"86d1c1fd30c28a6ea9bef59d3fce6a89bad20313c555a7775700a98220b5bca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:44.521277Z","signature_b64":"aIaSg36id1KXoPWUqI1XsO6bphZZCVPTBayn7WluGYarabWaSY3HAhoXDng1HXC3+YtaaMgHK69FUZ1BYMjmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3025c399a18aea5a366f1b73c6feeed157f85204d858d3b8ec8063a2f4b5636d","last_reissued_at":"2026-07-05T10:10:44.520868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:44.520868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the expressiveness and spectral bias of KANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan W. Siegel, Thomas Y. Hou, Yixuan Wang, Ziming Liu","submitted_at":"2024-10-02T17:57:38Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KAN) \\cite{liu2024kan} were very recently proposed as a potential alternative to the prevalent architectural backbone of many deep learning models, the multi-layer perceptron (MLP). KANs have seen success in various tasks of AI for science, with their empirical efficiency and accuracy demostrated in function regression, PDE solving, and many more scientific problems.\n  In this article, we revisit the comparison of KANs and MLPs, with emphasis on a theoretical perspective. On the one hand, we compare the representation and approximation capabilities of KANs and MLPs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01803","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/2410.01803/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":"2410.01803","created_at":"2026-07-05T10:10:44.520923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01803v2","created_at":"2026-07-05T10:10:44.520923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01803","created_at":"2026-07-05T10:10:44.520923+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAS4HGNBRLVF","created_at":"2026-07-05T10:10:44.520923+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAS4HGNBRLVFUNTP","created_at":"2026-07-05T10:10:44.520923+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAS4HGNB","created_at":"2026-07-05T10:10:44.520923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23179","citing_title":"EML Trees Are Universal Approximators","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24278","citing_title":"Fourier Feature Pyramids for Physics-Informed Neural Networks","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04435","citing_title":"QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":18,"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":37,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F","json":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F.json","graph_json":"https://pith.science/api/pith-number/GAS4HGNBRLVFUNTPDNZ4N7XO2F/graph.json","events_json":"https://pith.science/api/pith-number/GAS4HGNBRLVFUNTPDNZ4N7XO2F/events.json","paper":"https://pith.science/paper/GAS4HGNB"},"agent_actions":{"view_html":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F","download_json":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F.json","view_paper":"https://pith.science/paper/GAS4HGNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01803&json=true","fetch_graph":"https://pith.science/api/pith-number/GAS4HGNBRLVFUNTPDNZ4N7XO2F/graph.json","fetch_events":"https://pith.science/api/pith-number/GAS4HGNBRLVFUNTPDNZ4N7XO2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F/action/storage_attestation","attest_author":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F/action/author_attestation","sign_citation":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F/action/citation_signature","submit_replication":"https://pith.science/pith/GAS4HGNBRLVFUNTPDNZ4N7XO2F/action/replication_record"}},"created_at":"2026-07-05T10:10:44.520923+00:00","updated_at":"2026-07-05T10:10:44.520923+00:00"}