{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J7HBEVK7AMBCLQYHMCQUEEE3N5","short_pith_number":"pith:J7HBEVK7","schema_version":"1.0","canonical_sha256":"4fce12555f030225c30760a142109b6f4bef3e0aba0a93f6c706652093859bbc","source":{"kind":"arxiv","id":"2407.16674","version":2},"attestation_state":"computed","paper":{"title":"KAN or MLP: A Fairer Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Runpeng Yu, Weihao Yu, Xinchao Wang","submitted_at":"2024-07-23T17:43:35Z","abstract_excerpt":"This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and symbolic formula representation. Specifically, we control the number of parameters and FLOPs to compare the performance of KAN and MLP. Our main observation is that, except for symbolic formula representation tasks, MLP generally outperforms KAN. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation ma"},"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":"2407.16674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T17:43:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f88760443be65d6480129dac82159174089c2a49e3d6657c68b53d42a964cd6","abstract_canon_sha256":"76714c359f7a66f50d665206ed5e0983a0906829a0fa38d71b6cf9f78c915c4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:22.939968Z","signature_b64":"0tcLA0+jWhTcYivF77A+bdo8H/75eTS7ef1JAZFg+GZEZ9RJr7ND2JG2BAJMYeSrr/dvF63KA4pNWN4DSLzaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fce12555f030225c30760a142109b6f4bef3e0aba0a93f6c706652093859bbc","last_reissued_at":"2026-07-05T08:56:22.939414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:22.939414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAN or MLP: A Fairer Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Runpeng Yu, Weihao Yu, Xinchao Wang","submitted_at":"2024-07-23T17:43:35Z","abstract_excerpt":"This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and symbolic formula representation. Specifically, we control the number of parameters and FLOPs to compare the performance of KAN and MLP. Our main observation is that, except for symbolic formula representation tasks, MLP generally outperforms KAN. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16674","kind":"arxiv","version":2},"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/2407.16674/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":"2407.16674","created_at":"2026-07-05T08:56:22.939507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16674v2","created_at":"2026-07-05T08:56:22.939507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16674","created_at":"2026-07-05T08:56:22.939507+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7HBEVK7AMBC","created_at":"2026-07-05T08:56:22.939507+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7HBEVK7AMBCLQYH","created_at":"2026-07-05T08:56:22.939507+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7HBEVK7","created_at":"2026-07-05T08:56:22.939507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06959","citing_title":"KAN-LSTM-Transformer Neural Networks, MFV and Cosmological Parameters","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27042","citing_title":"Low Complexity Kolmogorov-Arnold Network-based DPD for Analog RoF Fronthaul","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27126","citing_title":"Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22258","citing_title":"From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2410.01990","citing_title":"Deep Learning Alternatives of the Kolmogorov Superposition Theorem","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2410.03801","citing_title":"P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21534","citing_title":"Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16750","citing_title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03345","citing_title":"Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5","json":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5.json","graph_json":"https://pith.science/api/pith-number/J7HBEVK7AMBCLQYHMCQUEEE3N5/graph.json","events_json":"https://pith.science/api/pith-number/J7HBEVK7AMBCLQYHMCQUEEE3N5/events.json","paper":"https://pith.science/paper/J7HBEVK7"},"agent_actions":{"view_html":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5","download_json":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5.json","view_paper":"https://pith.science/paper/J7HBEVK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16674&json=true","fetch_graph":"https://pith.science/api/pith-number/J7HBEVK7AMBCLQYHMCQUEEE3N5/graph.json","fetch_events":"https://pith.science/api/pith-number/J7HBEVK7AMBCLQYHMCQUEEE3N5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5/action/storage_attestation","attest_author":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5/action/author_attestation","sign_citation":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5/action/citation_signature","submit_replication":"https://pith.science/pith/J7HBEVK7AMBCLQYHMCQUEEE3N5/action/replication_record"}},"created_at":"2026-07-05T08:56:22.939507+00:00","updated_at":"2026-07-05T08:56:22.939507+00:00"}