{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27CTY3LO65G74IXDMUXHBVOBDY","short_pith_number":"pith:27CTY3LO","schema_version":"1.0","canonical_sha256":"d7c53c6d6ef74dfe22e3652e70d5c11e394ca9ba444c1148ff962e210bb08737","source":{"kind":"arxiv","id":"2406.14495","version":1},"attestation_state":"computed","paper":{"title":"rKAN: Rational Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Alireza Afzal Aghaei","submitted_at":"2024-06-20T16:59:38Z","abstract_excerpt":"The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves as their primary basis function, but their inherent complexity posed implementation challenges. Consequently, researchers have explored alternative basis functions such as Wavelets, Polynomials, and Fractional functions. In this research, we explore the use of rational functions as a novel basis function for KANs. We propose two different approaches based on Pade approximation and rational Jacobi functions as trainabl"},"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":"2406.14495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T16:59:38Z","cross_cats_sorted":["cs.NA","cs.NE","math.NA"],"title_canon_sha256":"3af44a23c7992bdc56c5b1b975ec429f47b67d60086fe450849c663b99a7538b","abstract_canon_sha256":"4582c901afcc3f30c56982cdf78c4633206b1c031b39a0f01cd64cf296a261fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:51.560465Z","signature_b64":"oyo/NVcfHyzSIkcNIIlg4RVXTPPoTBlemKL8wOagiSKQhnQ4xK/D8DcD+oIsZE/WKy14bj72b8zJGPhC0jVbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c53c6d6ef74dfe22e3652e70d5c11e394ca9ba444c1148ff962e210bb08737","last_reissued_at":"2026-07-05T08:34:51.560040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:51.560040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"rKAN: Rational Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Alireza Afzal Aghaei","submitted_at":"2024-06-20T16:59:38Z","abstract_excerpt":"The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves as their primary basis function, but their inherent complexity posed implementation challenges. Consequently, researchers have explored alternative basis functions such as Wavelets, Polynomials, and Fractional functions. In this research, we explore the use of rational functions as a novel basis function for KANs. We propose two different approaches based on Pade approximation and rational Jacobi functions as trainabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14495","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/2406.14495/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":"2406.14495","created_at":"2026-07-05T08:34:51.560095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14495v1","created_at":"2026-07-05T08:34:51.560095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14495","created_at":"2026-07-05T08:34:51.560095+00:00"},{"alias_kind":"pith_short_12","alias_value":"27CTY3LO65G7","created_at":"2026-07-05T08:34:51.560095+00:00"},{"alias_kind":"pith_short_16","alias_value":"27CTY3LO65G74IXD","created_at":"2026-07-05T08:34:51.560095+00:00"},{"alias_kind":"pith_short_8","alias_value":"27CTY3LO","created_at":"2026-07-05T08:34:51.560095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04435","citing_title":"QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04096","citing_title":"Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15250","citing_title":"In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY","json":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY.json","graph_json":"https://pith.science/api/pith-number/27CTY3LO65G74IXDMUXHBVOBDY/graph.json","events_json":"https://pith.science/api/pith-number/27CTY3LO65G74IXDMUXHBVOBDY/events.json","paper":"https://pith.science/paper/27CTY3LO"},"agent_actions":{"view_html":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY","download_json":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY.json","view_paper":"https://pith.science/paper/27CTY3LO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14495&json=true","fetch_graph":"https://pith.science/api/pith-number/27CTY3LO65G74IXDMUXHBVOBDY/graph.json","fetch_events":"https://pith.science/api/pith-number/27CTY3LO65G74IXDMUXHBVOBDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY/action/storage_attestation","attest_author":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY/action/author_attestation","sign_citation":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY/action/citation_signature","submit_replication":"https://pith.science/pith/27CTY3LO65G74IXDMUXHBVOBDY/action/replication_record"}},"created_at":"2026-07-05T08:34:51.560095+00:00","updated_at":"2026-07-05T08:34:51.560095+00:00"}