{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IP74UOYX2FCCZ2SAZMA4QGDYH4","short_pith_number":"pith:IP74UOYX","schema_version":"1.0","canonical_sha256":"43ffca3b17d1442cea40cb01c818783f026f99a0ec64bf18d8c225c144cb0ef2","source":{"kind":"arxiv","id":"2504.15110","version":3},"attestation_state":"computed","paper":{"title":"Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.FA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Bum Jun Kim, Takashi Furuya","submitted_at":"2025-04-21T14:02:59Z","abstract_excerpt":"Inspired by the Kolmogorov-Arnold superposition theorem, Kolmogorov-Arnold Networks (KANs) have recently emerged as an improved backbone for most deep learning frameworks, promising more adaptivity than their multilayer perceptron (MLP) predecessor by allowing for trainable spline-based activation functions. In this paper, we probe the theoretical foundations of the KAN architecture by showing that it can optimally approximate any Besov function in $B^{s}_{p,q}(\\mathcal{X})$ on a bounded open, or even fractal, domain $\\mathcal{X}$ in $\\mathbb{R}^d$ at the optimal approximation rate with respec"},"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":"2504.15110","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-21T14:02:59Z","cross_cats_sorted":["cs.NA","cs.NE","math.FA","math.NA","stat.ML"],"title_canon_sha256":"8bdf9adb18f347059d05061c991b3fd0491bd072747f18acb9c6d3f31e9d6cde","abstract_canon_sha256":"13778f163aeaf6f9c81811bbc162a73e8f59b35dbddb09746bc7c4083f715cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:33.181658Z","signature_b64":"za6LL6utMiPwzrxMuORreqt+MtBnpG3FXIzZrL5LZ8NKjcMqXxVBpsZkBZbmuUHk9vV4MovS160zZdWi4unpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ffca3b17d1442cea40cb01c818783f026f99a0ec64bf18d8c225c144cb0ef2","last_reissued_at":"2026-07-05T11:49:33.181143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:33.181143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.FA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Bum Jun Kim, Takashi Furuya","submitted_at":"2025-04-21T14:02:59Z","abstract_excerpt":"Inspired by the Kolmogorov-Arnold superposition theorem, Kolmogorov-Arnold Networks (KANs) have recently emerged as an improved backbone for most deep learning frameworks, promising more adaptivity than their multilayer perceptron (MLP) predecessor by allowing for trainable spline-based activation functions. In this paper, we probe the theoretical foundations of the KAN architecture by showing that it can optimally approximate any Besov function in $B^{s}_{p,q}(\\mathcal{X})$ on a bounded open, or even fractal, domain $\\mathcal{X}$ in $\\mathbb{R}^d$ at the optimal approximation rate with respec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15110","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/2504.15110/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":"2504.15110","created_at":"2026-07-05T11:49:33.181201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15110v3","created_at":"2026-07-05T11:49:33.181201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15110","created_at":"2026-07-05T11:49:33.181201+00:00"},{"alias_kind":"pith_short_12","alias_value":"IP74UOYX2FCC","created_at":"2026-07-05T11:49:33.181201+00:00"},{"alias_kind":"pith_short_16","alias_value":"IP74UOYX2FCCZ2SA","created_at":"2026-07-05T11:49:33.181201+00:00"},{"alias_kind":"pith_short_8","alias_value":"IP74UOYX","created_at":"2026-07-05T11:49:33.181201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23082","citing_title":"KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23082","citing_title":"KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":281,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23765","citing_title":"Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4","json":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4.json","graph_json":"https://pith.science/api/pith-number/IP74UOYX2FCCZ2SAZMA4QGDYH4/graph.json","events_json":"https://pith.science/api/pith-number/IP74UOYX2FCCZ2SAZMA4QGDYH4/events.json","paper":"https://pith.science/paper/IP74UOYX"},"agent_actions":{"view_html":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4","download_json":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4.json","view_paper":"https://pith.science/paper/IP74UOYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15110&json=true","fetch_graph":"https://pith.science/api/pith-number/IP74UOYX2FCCZ2SAZMA4QGDYH4/graph.json","fetch_events":"https://pith.science/api/pith-number/IP74UOYX2FCCZ2SAZMA4QGDYH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4/action/storage_attestation","attest_author":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4/action/author_attestation","sign_citation":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4/action/citation_signature","submit_replication":"https://pith.science/pith/IP74UOYX2FCCZ2SAZMA4QGDYH4/action/replication_record"}},"created_at":"2026-07-05T11:49:33.181201+00:00","updated_at":"2026-07-05T11:49:33.181201+00:00"}