{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GHMQWZCLN7TP5GSK4PVSBTHCNB","short_pith_number":"pith:GHMQWZCL","schema_version":"1.0","canonical_sha256":"31d90b644b6fe6fe9a4ae3eb20cce2685576f1f3357bdc6b1a6beb3362b6b901","source":{"kind":"arxiv","id":"2410.08026","version":2},"attestation_state":"computed","paper":{"title":"Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huijuan Zhou, Xianyang Zhang","submitted_at":"2024-10-10T15:23:21Z","abstract_excerpt":"Kolmogorov-Arnold Network (KAN) is a network structure recently proposed by Liu et al. (2024) that offers improved interpretability and a more parsimonious design in many science-oriented tasks compared to multi-layer perceptrons. This work provides a rigorous theoretical analysis of KAN by establishing generalization bounds for KAN equipped with activation functions that are either represented by linear combinations of basis functions or lying in a low-rank Reproducing Kernel Hilbert Space (RKHS). In the first case, the generalization bound accommodates various choices of basis functions in f"},"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":"2410.08026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T15:23:21Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"af88f386f95a36a5c7f71b54dc0d68666dedd21a61804cea7ffd0b3531959822","abstract_canon_sha256":"8a02ca7748178c649d6fce8f526a967a03f4561b41c10c0a25609c90de002423"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:15.360161Z","signature_b64":"wREKi26u4ofyBCISp4OiWMhU7m2s0rF+bMghFB8osmvq88lcqZDggVbJAX+AsFmAR/v3F5FbNUbJLTFkzM2iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d90b644b6fe6fe9a4ae3eb20cce2685576f1f3357bdc6b1a6beb3362b6b901","last_reissued_at":"2026-07-05T09:44:15.359628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:15.359628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huijuan Zhou, Xianyang Zhang","submitted_at":"2024-10-10T15:23:21Z","abstract_excerpt":"Kolmogorov-Arnold Network (KAN) is a network structure recently proposed by Liu et al. (2024) that offers improved interpretability and a more parsimonious design in many science-oriented tasks compared to multi-layer perceptrons. This work provides a rigorous theoretical analysis of KAN by establishing generalization bounds for KAN equipped with activation functions that are either represented by linear combinations of basis functions or lying in a low-rank Reproducing Kernel Hilbert Space (RKHS). In the first case, the generalization bound accommodates various choices of basis functions in f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08026","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/2410.08026/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":"2410.08026","created_at":"2026-07-05T09:44:15.359685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08026v2","created_at":"2026-07-05T09:44:15.359685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08026","created_at":"2026-07-05T09:44:15.359685+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHMQWZCLN7TP","created_at":"2026-07-05T09:44:15.359685+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHMQWZCLN7TP5GSK","created_at":"2026-07-05T09:44:15.359685+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHMQWZCL","created_at":"2026-07-05T09:44:15.359685+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":283,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB","json":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB.json","graph_json":"https://pith.science/api/pith-number/GHMQWZCLN7TP5GSK4PVSBTHCNB/graph.json","events_json":"https://pith.science/api/pith-number/GHMQWZCLN7TP5GSK4PVSBTHCNB/events.json","paper":"https://pith.science/paper/GHMQWZCL"},"agent_actions":{"view_html":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB","download_json":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB.json","view_paper":"https://pith.science/paper/GHMQWZCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08026&json=true","fetch_graph":"https://pith.science/api/pith-number/GHMQWZCLN7TP5GSK4PVSBTHCNB/graph.json","fetch_events":"https://pith.science/api/pith-number/GHMQWZCLN7TP5GSK4PVSBTHCNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB/action/storage_attestation","attest_author":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB/action/author_attestation","sign_citation":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB/action/citation_signature","submit_replication":"https://pith.science/pith/GHMQWZCLN7TP5GSK4PVSBTHCNB/action/replication_record"}},"created_at":"2026-07-05T09:44:15.359685+00:00","updated_at":"2026-07-05T09:44:15.359685+00:00"}