{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IC4IRCKGLUVWPFNSNDQ5PG5DHA","short_pith_number":"pith:IC4IRCKG","schema_version":"1.0","canonical_sha256":"40b88889465d2b6795b268e1d79ba338145175b876e7e734c1b930548825e9aa","source":{"kind":"arxiv","id":"2502.06018","version":3},"attestation_state":"computed","paper":{"title":"Kolmogorov-Arnold Fourier Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jusheng Zhang, Kaitong Cai, Keze Wang, Wenhao Wang, Yijia Fan","submitted_at":"2025-02-09T20:21:43Z","abstract_excerpt":"Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture high-frequency features in high-dimensional tasks. To address these issues, we propose the Kolmogorov-Arnold Fourier Network (KAF), which fundamentally redefines the KAN paradigm through spectral reparameterization. Our key contributions include: (1) proposing a fundamental basis transformation from the local, grid-based B-spline representation to a global, adaptive spectral representation. This shift changes the ne"},"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":"2502.06018","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T20:21:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"45b701af765055db620f9efd0b76ba489645a296fc2a8fd0b98b17f4198a4d18","abstract_canon_sha256":"9c580ea24c886ba802ba06ecdd4f712eac0483469172deb7dbd8637c99143cd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:48.469641Z","signature_b64":"Dh9A/UUqsrx/kFj14GJsLUZemgWqGyRJIku47Q8tlcIXbyDU59/HJZLFJnUEol7yU89qkVxjun+PVz7WEOWBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40b88889465d2b6795b268e1d79ba338145175b876e7e734c1b930548825e9aa","last_reissued_at":"2026-05-26T02:03:48.468750Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:48.468750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kolmogorov-Arnold Fourier Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jusheng Zhang, Kaitong Cai, Keze Wang, Wenhao Wang, Yijia Fan","submitted_at":"2025-02-09T20:21:43Z","abstract_excerpt":"Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture high-frequency features in high-dimensional tasks. To address these issues, we propose the Kolmogorov-Arnold Fourier Network (KAF), which fundamentally redefines the KAN paradigm through spectral reparameterization. Our key contributions include: (1) proposing a fundamental basis transformation from the local, grid-based B-spline representation to a global, adaptive spectral representation. This shift changes the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06018","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/2502.06018/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":"2502.06018","created_at":"2026-05-26T02:03:48.468881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06018v3","created_at":"2026-05-26T02:03:48.468881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06018","created_at":"2026-05-26T02:03:48.468881+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC4IRCKGLUVW","created_at":"2026-05-26T02:03:48.468881+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC4IRCKGLUVWPFNS","created_at":"2026-05-26T02:03:48.468881+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC4IRCKG","created_at":"2026-05-26T02:03:48.468881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.21534","citing_title":"Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09726","citing_title":"Forgetting as a Feature: Cognitive Alignment of Large Language Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23599","citing_title":"Partition-of-Unity Gaussian Kolmogorov-Arnold Networks","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23625","citing_title":"Physics informed operator learning of parameter dependent spectra","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21174","citing_title":"Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA","json":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA.json","graph_json":"https://pith.science/api/pith-number/IC4IRCKGLUVWPFNSNDQ5PG5DHA/graph.json","events_json":"https://pith.science/api/pith-number/IC4IRCKGLUVWPFNSNDQ5PG5DHA/events.json","paper":"https://pith.science/paper/IC4IRCKG"},"agent_actions":{"view_html":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA","download_json":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA.json","view_paper":"https://pith.science/paper/IC4IRCKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06018&json=true","fetch_graph":"https://pith.science/api/pith-number/IC4IRCKGLUVWPFNSNDQ5PG5DHA/graph.json","fetch_events":"https://pith.science/api/pith-number/IC4IRCKGLUVWPFNSNDQ5PG5DHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA/action/storage_attestation","attest_author":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA/action/author_attestation","sign_citation":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA/action/citation_signature","submit_replication":"https://pith.science/pith/IC4IRCKGLUVWPFNSNDQ5PG5DHA/action/replication_record"}},"created_at":"2026-05-26T02:03:48.468881+00:00","updated_at":"2026-05-26T02:03:48.468881+00:00"}