{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YH6UOZYAPJZJSN5SQLGTJPU56T","short_pith_number":"pith:YH6UOZYA","schema_version":"1.0","canonical_sha256":"c1fd4767007a729937b282cd34be9df4de880f1cffdc83c38c51a2190e08d374","source":{"kind":"arxiv","id":"2406.02917","version":1},"attestation_state":"computed","paper":{"title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"George Em Karniadakis, Juan Diego Toscano, Khemraj Shukla, Zhicheng Wang, Zongren Zou","submitted_at":"2024-06-05T04:10:36Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) were recently introduced as an alternative representation model to MLP. Herein, we employ KANs to construct physics-informed machine learning models (PIKANs) and deep operator models (DeepOKANs) for solving differential equations for forward and inverse problems. In particular, we compare them with physics-informed neural networks (PINNs) and deep operator networks (DeepONets), which are based on the standard MLP representation. We find that although the original KANs based on the B-splines parameterization lack accuracy and efficiency, modified versions based"},"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":"2406.02917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T04:10:36Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"668ea2748534668536b311119719c3485cdae4d5b5a4fb7f56dd5f86a2f37b6f","abstract_canon_sha256":"41afcdccb508a8a42bd100b016c535b8f64c9ebd72534fb47139a8a8424bcf1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:32.657275Z","signature_b64":"hNiqn7OUMG9cC+aPprc+LjxG3/Ea2YLfnHPdIoPaqdLzY4bpELEoOw5HNds02UqMQz9diEWIqPFrwFtxoyIoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1fd4767007a729937b282cd34be9df4de880f1cffdc83c38c51a2190e08d374","last_reissued_at":"2026-07-05T08:27:32.656804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:32.656804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"George Em Karniadakis, Juan Diego Toscano, Khemraj Shukla, Zhicheng Wang, Zongren Zou","submitted_at":"2024-06-05T04:10:36Z","abstract_excerpt":"Kolmogorov-Arnold Networks (KANs) were recently introduced as an alternative representation model to MLP. Herein, we employ KANs to construct physics-informed machine learning models (PIKANs) and deep operator models (DeepOKANs) for solving differential equations for forward and inverse problems. In particular, we compare them with physics-informed neural networks (PINNs) and deep operator networks (DeepONets), which are based on the standard MLP representation. We find that although the original KANs based on the B-splines parameterization lack accuracy and efficiency, modified versions based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02917","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/2406.02917/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":"2406.02917","created_at":"2026-07-05T08:27:32.656865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02917v1","created_at":"2026-07-05T08:27:32.656865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02917","created_at":"2026-07-05T08:27:32.656865+00:00"},{"alias_kind":"pith_short_12","alias_value":"YH6UOZYAPJZJ","created_at":"2026-07-05T08:27:32.656865+00:00"},{"alias_kind":"pith_short_16","alias_value":"YH6UOZYAPJZJSN5S","created_at":"2026-07-05T08:27:32.656865+00:00"},{"alias_kind":"pith_short_8","alias_value":"YH6UOZYA","created_at":"2026-07-05T08:27:32.656865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24278","citing_title":"Fourier Feature Pyramids for Physics-Informed Neural Networks","ref_index":21,"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":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13746","citing_title":"Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Network","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T","json":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T.json","graph_json":"https://pith.science/api/pith-number/YH6UOZYAPJZJSN5SQLGTJPU56T/graph.json","events_json":"https://pith.science/api/pith-number/YH6UOZYAPJZJSN5SQLGTJPU56T/events.json","paper":"https://pith.science/paper/YH6UOZYA"},"agent_actions":{"view_html":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T","download_json":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T.json","view_paper":"https://pith.science/paper/YH6UOZYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02917&json=true","fetch_graph":"https://pith.science/api/pith-number/YH6UOZYAPJZJSN5SQLGTJPU56T/graph.json","fetch_events":"https://pith.science/api/pith-number/YH6UOZYAPJZJSN5SQLGTJPU56T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T/action/storage_attestation","attest_author":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T/action/author_attestation","sign_citation":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T/action/citation_signature","submit_replication":"https://pith.science/pith/YH6UOZYAPJZJSN5SQLGTJPU56T/action/replication_record"}},"created_at":"2026-07-05T08:27:32.656865+00:00","updated_at":"2026-07-05T08:27:32.656865+00:00"}