{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CGB5XFIUP27WX4OBB2O2BK5NAP","short_pith_number":"pith:CGB5XFIU","schema_version":"1.0","canonical_sha256":"1183db95147ebf6bf1c10e9da0abad03cec7eb276ae3eaf39e54cfcde89f09cd","source":{"kind":"arxiv","id":"2409.10463","version":1},"attestation_state":"computed","paper":{"title":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Farhad Pourkamali-Anaraki","submitted_at":"2024-09-16T16:56:08Z","abstract_excerpt":"Multilayer Perceptrons (MLPs) have long been a cornerstone in deep learning, known for their capacity to model complex relationships. Recently, Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative, utilizing highly flexible learnable activation functions directly on network edges, a departure from the neuron-centric approach of MLPs. However, KANs significantly increase the number of learnable parameters, raising concerns about their effectiveness in data-scarce environments. This paper presents a comprehensive comparative study of MLPs and KANs from both algorithmic and "},"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":"2409.10463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-16T16:56:08Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"237055227ee08395bd8a5bdd205df859d6f251bfd26c1a73d3c974e83326642d","abstract_canon_sha256":"e63e1c33ab8d31584c111bffd33fa12fe8e383c981f42d9f603b86f7f56b7cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:40.520528Z","signature_b64":"6839umSk0B7wpuU0GN5VK6RVKcZEPNCI0EWzccazgo/TFYYKxcbq0Q5Ublmt/9n9Imb6fSAeRCH822Q0/A6TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1183db95147ebf6bf1c10e9da0abad03cec7eb276ae3eaf39e54cfcde89f09cd","last_reissued_at":"2026-07-05T09:07:40.520014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:40.520014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Farhad Pourkamali-Anaraki","submitted_at":"2024-09-16T16:56:08Z","abstract_excerpt":"Multilayer Perceptrons (MLPs) have long been a cornerstone in deep learning, known for their capacity to model complex relationships. Recently, Kolmogorov-Arnold Networks (KANs) have emerged as a compelling alternative, utilizing highly flexible learnable activation functions directly on network edges, a departure from the neuron-centric approach of MLPs. However, KANs significantly increase the number of learnable parameters, raising concerns about their effectiveness in data-scarce environments. This paper presents a comprehensive comparative study of MLPs and KANs from both algorithmic and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10463","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/2409.10463/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":"2409.10463","created_at":"2026-07-05T09:07:40.520069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10463v1","created_at":"2026-07-05T09:07:40.520069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10463","created_at":"2026-07-05T09:07:40.520069+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGB5XFIUP27W","created_at":"2026-07-05T09:07:40.520069+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGB5XFIUP27WX4OB","created_at":"2026-07-05T09:07:40.520069+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGB5XFIU","created_at":"2026-07-05T09:07:40.520069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20349","citing_title":"Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20349","citing_title":"Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP","json":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP.json","graph_json":"https://pith.science/api/pith-number/CGB5XFIUP27WX4OBB2O2BK5NAP/graph.json","events_json":"https://pith.science/api/pith-number/CGB5XFIUP27WX4OBB2O2BK5NAP/events.json","paper":"https://pith.science/paper/CGB5XFIU"},"agent_actions":{"view_html":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP","download_json":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP.json","view_paper":"https://pith.science/paper/CGB5XFIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10463&json=true","fetch_graph":"https://pith.science/api/pith-number/CGB5XFIUP27WX4OBB2O2BK5NAP/graph.json","fetch_events":"https://pith.science/api/pith-number/CGB5XFIUP27WX4OBB2O2BK5NAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP/action/storage_attestation","attest_author":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP/action/author_attestation","sign_citation":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP/action/citation_signature","submit_replication":"https://pith.science/pith/CGB5XFIUP27WX4OBB2O2BK5NAP/action/replication_record"}},"created_at":"2026-07-05T09:07:40.520069+00:00","updated_at":"2026-07-05T09:07:40.520069+00:00"}