{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3TS5XRJWTNI7UNV5A3ERRPONJ","short_pith_number":"pith:P3TS5XRJ","schema_version":"1.0","canonical_sha256":"7ee72ede29b4da8fd1b5e83648c5ee6a581450d4f46dd71d09266d0cc9d89d9a","source":{"kind":"arxiv","id":"2605.21534","version":1},"attestation_state":"computed","paper":{"title":"Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adeeba Haider, Alessandra De Rossi, Amir Noorizadegan, Roberto Cavoretto","submitted_at":"2026-05-20T01:28:34Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline bases. Although effective, spline-based implementations can be computationally expensive. A modified version of KANs, called FastKAN, improves efficiency by replacing splines with Gaussian radial basis functions (RBFs), but it relies on a fixed kernel and shape parameter. In this work, we extend the RBF-based KAN framework by introducing a broader family of radial basis kernels and by initializing the kernel shape parameter using leave-one-out cros"},"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":"2605.21534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-20T01:28:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1e338c7689eb4635dca120f66532a025b0729295961de3373847ec68ee8764d6","abstract_canon_sha256":"e54b459dc54fd5ca08107dcf39fc37dbf794a153b3743d7771f49450ece7a644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T00:02:27.836557Z","signature_b64":"nNqrqs2foWNY91K/uyCixo4bmylasGASPqbvkQfN0J9WqDyEotuohi5Ay8oCMBBCiiKTInBv64bnZ7Pl3Jv0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ee72ede29b4da8fd1b5e83648c5ee6a581450d4f46dd71d09266d0cc9d89d9a","last_reissued_at":"2026-05-22T00:02:27.836137Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T00:02:27.836137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adeeba Haider, Alessandra De Rossi, Amir Noorizadegan, Roberto Cavoretto","submitted_at":"2026-05-20T01:28:34Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline bases. Although effective, spline-based implementations can be computationally expensive. A modified version of KANs, called FastKAN, improves efficiency by replacing splines with Gaussian radial basis functions (RBFs), but it relies on a fixed kernel and shape parameter. In this work, we extend the RBF-based KAN framework by introducing a broader family of radial basis kernels and by initializing the kernel shape parameter using leave-one-out cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21534","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/2605.21534/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":"2605.21534","created_at":"2026-05-22T00:02:27.836195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21534v1","created_at":"2026-05-22T00:02:27.836195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21534","created_at":"2026-05-22T00:02:27.836195+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3TS5XRJWTNI","created_at":"2026-05-22T00:02:27.836195+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3TS5XRJWTNI7UNV","created_at":"2026-05-22T00:02:27.836195+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3TS5XRJ","created_at":"2026-05-22T00:02:27.836195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ","json":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ.json","graph_json":"https://pith.science/api/pith-number/P3TS5XRJWTNI7UNV5A3ERRPONJ/graph.json","events_json":"https://pith.science/api/pith-number/P3TS5XRJWTNI7UNV5A3ERRPONJ/events.json","paper":"https://pith.science/paper/P3TS5XRJ"},"agent_actions":{"view_html":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ","download_json":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ.json","view_paper":"https://pith.science/paper/P3TS5XRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21534&json=true","fetch_graph":"https://pith.science/api/pith-number/P3TS5XRJWTNI7UNV5A3ERRPONJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P3TS5XRJWTNI7UNV5A3ERRPONJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ/action/storage_attestation","attest_author":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ/action/author_attestation","sign_citation":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ/action/citation_signature","submit_replication":"https://pith.science/pith/P3TS5XRJWTNI7UNV5A3ERRPONJ/action/replication_record"}},"created_at":"2026-05-22T00:02:27.836195+00:00","updated_at":"2026-05-22T00:02:27.836195+00:00"}