{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AMCDAJTLGPUGTHN4B6OFW52SI6","short_pith_number":"pith:AMCDAJTL","schema_version":"1.0","canonical_sha256":"030430266b33e8699dbc0f9c5b775247a9b74539f0b8c76531ed9fb8c4feb993","source":{"kind":"arxiv","id":"2407.13044","version":4},"attestation_state":"computed","paper":{"title":"DropKAN: Regularizing KANs by masking post-activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mohammed Ghaith Altarabichi","submitted_at":"2024-07-17T22:48:47Z","abstract_excerpt":"We propose DropKAN (Dropout Kolmogorov-Arnold Networks) a regularization method that prevents co-adaptation of activation function weights in Kolmogorov-Arnold Networks (KANs). DropKAN functions by embedding the drop mask directly within the KAN layer, randomly masking the outputs of some activations within the KANs' computation graph. We show that this simple procedure that require minimal coding effort has a regularizing effect and consistently lead to better generalization of KANs. We analyze the adaptation of the standard Dropout with KANs and demonstrate that Dropout applied to KANs' neur"},"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":"2407.13044","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T22:48:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"070c94adf5e02ae6457251be764aeda6e25c3338aa729dbdb9980d6141608b98","abstract_canon_sha256":"0ce3890d0d5a4223f51391140549a491bf17e892d9893f2a5e1228cd79df4018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:05.712269Z","signature_b64":"d/mUwJxq6tDhiCJFBuwMlI5+iy6rMmEKX1RxlX9hIKGCDzTsxWlNRpRCoXuAhIMBjVSB8+KGfk6iy16xePJiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030430266b33e8699dbc0f9c5b775247a9b74539f0b8c76531ed9fb8c4feb993","last_reissued_at":"2026-07-05T08:57:05.711796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:05.711796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropKAN: Regularizing KANs by masking post-activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mohammed Ghaith Altarabichi","submitted_at":"2024-07-17T22:48:47Z","abstract_excerpt":"We propose DropKAN (Dropout Kolmogorov-Arnold Networks) a regularization method that prevents co-adaptation of activation function weights in Kolmogorov-Arnold Networks (KANs). DropKAN functions by embedding the drop mask directly within the KAN layer, randomly masking the outputs of some activations within the KANs' computation graph. We show that this simple procedure that require minimal coding effort has a regularizing effect and consistently lead to better generalization of KANs. We analyze the adaptation of the standard Dropout with KANs and demonstrate that Dropout applied to KANs' neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13044","kind":"arxiv","version":4},"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/2407.13044/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":"2407.13044","created_at":"2026-07-05T08:57:05.711853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13044v4","created_at":"2026-07-05T08:57:05.711853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13044","created_at":"2026-07-05T08:57:05.711853+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMCDAJTLGPUG","created_at":"2026-07-05T08:57:05.711853+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMCDAJTLGPUGTHN4","created_at":"2026-07-05T08:57:05.711853+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMCDAJTL","created_at":"2026-07-05T08:57:05.711853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19031","citing_title":"KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19031","citing_title":"KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16750","citing_title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":233,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6","json":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6.json","graph_json":"https://pith.science/api/pith-number/AMCDAJTLGPUGTHN4B6OFW52SI6/graph.json","events_json":"https://pith.science/api/pith-number/AMCDAJTLGPUGTHN4B6OFW52SI6/events.json","paper":"https://pith.science/paper/AMCDAJTL"},"agent_actions":{"view_html":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6","download_json":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6.json","view_paper":"https://pith.science/paper/AMCDAJTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13044&json=true","fetch_graph":"https://pith.science/api/pith-number/AMCDAJTLGPUGTHN4B6OFW52SI6/graph.json","fetch_events":"https://pith.science/api/pith-number/AMCDAJTLGPUGTHN4B6OFW52SI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6/action/storage_attestation","attest_author":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6/action/author_attestation","sign_citation":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6/action/citation_signature","submit_replication":"https://pith.science/pith/AMCDAJTLGPUGTHN4B6OFW52SI6/action/replication_record"}},"created_at":"2026-07-05T08:57:05.711853+00:00","updated_at":"2026-07-05T08:57:05.711853+00:00"}