{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3XPZ5NBIYFUN4POXG576554FNX","short_pith_number":"pith:3XPZ5NBI","schema_version":"1.0","canonical_sha256":"dddf9eb428c168de3dd7377feef7856df474adb596f590ac1d4d64bfc0af19c4","source":{"kind":"arxiv","id":"2412.16738","version":1},"attestation_state":"computed","paper":{"title":"KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"George Em Karniadakis, Juan Diego Toscano, Li-Lian Wang","submitted_at":"2024-12-21T19:01:38Z","abstract_excerpt":"Inspired by the Kolmogorov-Arnold representation theorem and Kurkova's principle of using approximate representations, we propose the Kurkova-Kolmogorov-Arnold Network (KKAN), a new two-block architecture that combines robust multi-layer perceptron (MLP) based inner functions with flexible linear combinations of basis functions as outer functions. We first prove that KKAN is a universal approximator, and then we demonstrate its versatility across scientific machine-learning applications, including function regression, physics-informed machine learning (PIML), and operator-learning frameworks. "},"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":"2412.16738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T19:01:38Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"c86baae26974519738bc829b2f627b4d1cc3560be141c0ea0e2d939bc2cae13d","abstract_canon_sha256":"b5d3474d2dd24945864fa32a584ccd9ef7cfa46c9f78a35137297f56aa230e9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:12.453103Z","signature_b64":"bHDZ+xxvK2GYPg+di8qnJBJYLkBmLRwYI11hdmETJGlpjUB9171ZP5HP5k3vDIxPKNszWxPfISbwbdv+OV/WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dddf9eb428c168de3dd7377feef7856df474adb596f590ac1d4d64bfc0af19c4","last_reissued_at":"2026-07-05T09:53:12.452642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:12.452642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"George Em Karniadakis, Juan Diego Toscano, Li-Lian Wang","submitted_at":"2024-12-21T19:01:38Z","abstract_excerpt":"Inspired by the Kolmogorov-Arnold representation theorem and Kurkova's principle of using approximate representations, we propose the Kurkova-Kolmogorov-Arnold Network (KKAN), a new two-block architecture that combines robust multi-layer perceptron (MLP) based inner functions with flexible linear combinations of basis functions as outer functions. We first prove that KKAN is a universal approximator, and then we demonstrate its versatility across scientific machine-learning applications, including function regression, physics-informed machine learning (PIML), and operator-learning frameworks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16738","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/2412.16738/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":"2412.16738","created_at":"2026-07-05T09:53:12.452696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16738v1","created_at":"2026-07-05T09:53:12.452696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16738","created_at":"2026-07-05T09:53:12.452696+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XPZ5NBIYFUN","created_at":"2026-07-05T09:53:12.452696+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XPZ5NBIYFUN4POX","created_at":"2026-07-05T09:53:12.452696+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XPZ5NBI","created_at":"2026-07-05T09:53:12.452696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02762","citing_title":"Scaled-cPIKANs: Domain Scaling in Chebyshev-based Physics-informed Kolmogorov-Arnold Networks","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX","json":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX.json","graph_json":"https://pith.science/api/pith-number/3XPZ5NBIYFUN4POXG576554FNX/graph.json","events_json":"https://pith.science/api/pith-number/3XPZ5NBIYFUN4POXG576554FNX/events.json","paper":"https://pith.science/paper/3XPZ5NBI"},"agent_actions":{"view_html":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX","download_json":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX.json","view_paper":"https://pith.science/paper/3XPZ5NBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16738&json=true","fetch_graph":"https://pith.science/api/pith-number/3XPZ5NBIYFUN4POXG576554FNX/graph.json","fetch_events":"https://pith.science/api/pith-number/3XPZ5NBIYFUN4POXG576554FNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX/action/storage_attestation","attest_author":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX/action/author_attestation","sign_citation":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX/action/citation_signature","submit_replication":"https://pith.science/pith/3XPZ5NBIYFUN4POXG576554FNX/action/replication_record"}},"created_at":"2026-07-05T09:53:12.452696+00:00","updated_at":"2026-07-05T09:53:12.452696+00:00"}