{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIHIGRG5GPP7XIF37V6NRIXMAQ","short_pith_number":"pith:SIHIGRG5","schema_version":"1.0","canonical_sha256":"920e8344dd33dffba0bbfd7cd8a2ec043b88034c410c25a615b10f9285575d75","source":{"kind":"arxiv","id":"2406.13155","version":3},"attestation_state":"computed","paper":{"title":"Convolutional Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Dylan Bodner, Antonio Santiago Tepsich, Jack Natan Spolski, Santiago Pourteau","submitted_at":"2024-06-19T02:09:44Z","abstract_excerpt":"In this paper, we present Convolutional Kolmogorov-Arnold Networks, a novel architecture that integrates the learnable spline-based activation functions of Kolmogorov-Arnold Networks (KANs) into convolutional layers. By replacing traditional fixed-weight kernels with learnable non-linear functions, Convolutional KANs offer a significant improvement in parameter efficiency and expressive power over standard Convolutional Neural Networks (CNNs). We empirically evaluate Convolutional KANs on the Fashion-MNIST dataset, demonstrating competitive accuracy with up to 50% fewer parameters compared to "},"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":"2406.13155","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T02:09:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74e4d62b9802efde5e7ef6b47956f9416b43ee09120ddd59344b6a84fc43f45b","abstract_canon_sha256":"e9a72dc9ce3a7695649e5abeac723f2d02ef2fd9bdf8d18cea360b314f32762c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:47.067446Z","signature_b64":"NACPmqckGNsg3os3AL2K3h8Rrpg1936AxTDlh/fE+i5b7jqW2c1yCbG8pqw2qznDFj/vDKO3rpZpreqRMETbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"920e8344dd33dffba0bbfd7cd8a2ec043b88034c410c25a615b10f9285575d75","last_reissued_at":"2026-07-05T10:41:47.066902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:47.066902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Dylan Bodner, Antonio Santiago Tepsich, Jack Natan Spolski, Santiago Pourteau","submitted_at":"2024-06-19T02:09:44Z","abstract_excerpt":"In this paper, we present Convolutional Kolmogorov-Arnold Networks, a novel architecture that integrates the learnable spline-based activation functions of Kolmogorov-Arnold Networks (KANs) into convolutional layers. By replacing traditional fixed-weight kernels with learnable non-linear functions, Convolutional KANs offer a significant improvement in parameter efficiency and expressive power over standard Convolutional Neural Networks (CNNs). We empirically evaluate Convolutional KANs on the Fashion-MNIST dataset, demonstrating competitive accuracy with up to 50% fewer parameters compared to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13155","kind":"arxiv","version":3},"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/2406.13155/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":"2406.13155","created_at":"2026-07-05T10:41:47.066969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13155v3","created_at":"2026-07-05T10:41:47.066969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13155","created_at":"2026-07-05T10:41:47.066969+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIHIGRG5GPP7","created_at":"2026-07-05T10:41:47.066969+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIHIGRG5GPP7XIF3","created_at":"2026-07-05T10:41:47.066969+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIHIGRG5","created_at":"2026-07-05T10:41:47.066969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06959","citing_title":"KAN-LSTM-Transformer Neural Networks, MFV and Cosmological Parameters","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24371","citing_title":"Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs","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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04435","citing_title":"QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation","ref_index":13,"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":3,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05193","citing_title":"RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16750","citing_title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05477","citing_title":"GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22409","citing_title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10046","citing_title":"PixelFlowCast: Latent-Free Precipitation Nowcasting via Pixel Mean Flows","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09572","citing_title":"KAN Text to Vision? The Exploration of Kolmogorov-Arnold Networks for Multi-Scale Sequence-Based Pose Animation from Sign Language Notation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23320","citing_title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01459","citing_title":"SRGAN-CKAN: Expressive Super-Resolution with Nonlinear Functional Operators under Minimal Resources","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01459","citing_title":"SRGAN-CKAN: Expressive Super-Resolution with Nonlinear Functional Operators under Minimal Resources","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ","json":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ.json","graph_json":"https://pith.science/api/pith-number/SIHIGRG5GPP7XIF37V6NRIXMAQ/graph.json","events_json":"https://pith.science/api/pith-number/SIHIGRG5GPP7XIF37V6NRIXMAQ/events.json","paper":"https://pith.science/paper/SIHIGRG5"},"agent_actions":{"view_html":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ","download_json":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ.json","view_paper":"https://pith.science/paper/SIHIGRG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13155&json=true","fetch_graph":"https://pith.science/api/pith-number/SIHIGRG5GPP7XIF37V6NRIXMAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SIHIGRG5GPP7XIF37V6NRIXMAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ/action/storage_attestation","attest_author":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ/action/author_attestation","sign_citation":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ/action/citation_signature","submit_replication":"https://pith.science/pith/SIHIGRG5GPP7XIF37V6NRIXMAQ/action/replication_record"}},"created_at":"2026-07-05T10:41:47.066969+00:00","updated_at":"2026-07-05T10:41:47.066969+00:00"}