{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YI43EFS5WHDAB6CEXDLHN5325G","short_pith_number":"pith:YI43EFS5","schema_version":"1.0","canonical_sha256":"c239b2165db1c600f844b8d676f77ae9a34ffef8409aaac9e8296610341cbd28","source":{"kind":"arxiv","id":"2501.09283","version":1},"attestation_state":"computed","paper":{"title":"Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liangwewi Nathan Zheng, Lin Yue, Miao Xu, Olaf Maennel, Wei Emma Zhang, Weitong Chen","submitted_at":"2025-01-16T04:12:05Z","abstract_excerpt":"Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stability and heavy trainable parameter. Furthermore, there is limited understanding of the behavior of the learned activation functions derived from B-splines. In this work, we analyze the behavior of KANs through the lens of spline knots and derive the lower and upper bound for the number of knots in B-spline-based KANs. To address existing limitations, we propose a novel Free Knots KAN that enhances the performance of th"},"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":"2501.09283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T04:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"213ffb72a90336ba769bbca495815b1f6fc311201cbea5b741ba67ef010cd0fb","abstract_canon_sha256":"5050054a3c3eac6dad5cd2d31ad27c74ebf08baa00a2d3548df8c94ddb8c9882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:44.607769Z","signature_b64":"0wYvwk13b9TSpF2wEyDHqGFtTGCsdJ9KjjQmnhQVycEga5+vWmxkAEnuOavu2qV5hwrqhvfEtFGNGnBmkVXQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c239b2165db1c600f844b8d676f77ae9a34ffef8409aaac9e8296610341cbd28","last_reissued_at":"2026-07-05T10:01:44.607236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:44.607236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liangwewi Nathan Zheng, Lin Yue, Miao Xu, Olaf Maennel, Wei Emma Zhang, Weitong Chen","submitted_at":"2025-01-16T04:12:05Z","abstract_excerpt":"Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stability and heavy trainable parameter. Furthermore, there is limited understanding of the behavior of the learned activation functions derived from B-splines. In this work, we analyze the behavior of KANs through the lens of spline knots and derive the lower and upper bound for the number of knots in B-spline-based KANs. To address existing limitations, we propose a novel Free Knots KAN that enhances the performance of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09283","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/2501.09283/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":"2501.09283","created_at":"2026-07-05T10:01:44.607300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09283v1","created_at":"2026-07-05T10:01:44.607300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09283","created_at":"2026-07-05T10:01:44.607300+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI43EFS5WHDA","created_at":"2026-07-05T10:01:44.607300+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI43EFS5WHDAB6CE","created_at":"2026-07-05T10:01:44.607300+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI43EFS5","created_at":"2026-07-05T10:01:44.607300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05635","citing_title":"From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G","json":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G.json","graph_json":"https://pith.science/api/pith-number/YI43EFS5WHDAB6CEXDLHN5325G/graph.json","events_json":"https://pith.science/api/pith-number/YI43EFS5WHDAB6CEXDLHN5325G/events.json","paper":"https://pith.science/paper/YI43EFS5"},"agent_actions":{"view_html":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G","download_json":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G.json","view_paper":"https://pith.science/paper/YI43EFS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09283&json=true","fetch_graph":"https://pith.science/api/pith-number/YI43EFS5WHDAB6CEXDLHN5325G/graph.json","fetch_events":"https://pith.science/api/pith-number/YI43EFS5WHDAB6CEXDLHN5325G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G/action/storage_attestation","attest_author":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G/action/author_attestation","sign_citation":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G/action/citation_signature","submit_replication":"https://pith.science/pith/YI43EFS5WHDAB6CEXDLHN5325G/action/replication_record"}},"created_at":"2026-07-05T10:01:44.607300+00:00","updated_at":"2026-07-05T10:01:44.607300+00:00"}