{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CL6AOOAYTEEOJW3RRONOUZ5Q7S","short_pith_number":"pith:CL6AOOAY","schema_version":"1.0","canonical_sha256":"12fc0738189908e4db718b9aea67b0fca59ce1382f08e543396bc1b2ddbe6f90","source":{"kind":"arxiv","id":"2409.10594","version":1},"attestation_state":"computed","paper":{"title":"Kolmogorov-Arnold Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Xinchao Wang, Xingyi Yang","submitted_at":"2024-09-16T17:54:51Z","abstract_excerpt":"Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is "},"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":"2409.10594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-16T17:54:51Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"136526c8a3bb0e155abd81f5325ffada90f96bf8d25cd59928296de5a2f8d7d7","abstract_canon_sha256":"05f310f7a27a05eef275b32bec9cc8b1879b32e95459dfe528780ca4b6b69784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:53.515689Z","signature_b64":"Fe4bJ8aj+yBtN88ZzzZEVgNbQDKRfYR13BRiQD08eHmA8GEzVU51Fshn+ZnWmWwvEXC03sRAfb9DUKRc5Jd8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12fc0738189908e4db718b9aea67b0fca59ce1382f08e543396bc1b2ddbe6f90","last_reissued_at":"2026-07-05T09:07:53.515141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:53.515141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kolmogorov-Arnold Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Xinchao Wang, Xingyi Yang","submitted_at":"2024-09-16T17:54:51Z","abstract_excerpt":"Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10594","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/2409.10594/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":"2409.10594","created_at":"2026-07-05T09:07:53.515202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10594v1","created_at":"2026-07-05T09:07:53.515202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10594","created_at":"2026-07-05T09:07:53.515202+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL6AOOAYTEEO","created_at":"2026-07-05T09:07:53.515202+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL6AOOAYTEEOJW3R","created_at":"2026-07-05T09:07:53.515202+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL6AOOAY","created_at":"2026-07-05T09:07:53.515202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2405.02068","citing_title":"Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection","ref_index":10,"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":29,"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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23056","citing_title":"FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10858","citing_title":"Tensor-based Multi-layer Decoupling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15654","citing_title":"From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02190","citing_title":"KANs need curvature: penalties for compositional smoothness","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S","json":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S.json","graph_json":"https://pith.science/api/pith-number/CL6AOOAYTEEOJW3RRONOUZ5Q7S/graph.json","events_json":"https://pith.science/api/pith-number/CL6AOOAYTEEOJW3RRONOUZ5Q7S/events.json","paper":"https://pith.science/paper/CL6AOOAY"},"agent_actions":{"view_html":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S","download_json":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S.json","view_paper":"https://pith.science/paper/CL6AOOAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10594&json=true","fetch_graph":"https://pith.science/api/pith-number/CL6AOOAYTEEOJW3RRONOUZ5Q7S/graph.json","fetch_events":"https://pith.science/api/pith-number/CL6AOOAYTEEOJW3RRONOUZ5Q7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S/action/storage_attestation","attest_author":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S/action/author_attestation","sign_citation":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S/action/citation_signature","submit_replication":"https://pith.science/pith/CL6AOOAYTEEOJW3RRONOUZ5Q7S/action/replication_record"}},"created_at":"2026-07-05T09:07:53.515202+00:00","updated_at":"2026-07-05T09:07:53.515202+00:00"}