{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76PGMNJNDVSU3NTG7C3WCNWGMA","short_pith_number":"pith:76PGMNJN","schema_version":"1.0","canonical_sha256":"ff9e66352d1d654db666f8b76136c66022411e4bf4824b398e767cf661917a5f","source":{"kind":"arxiv","id":"2408.08338","version":1},"attestation_state":"computed","paper":{"title":"Activation Space Selectable Kolmogorov-Arnold Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiansong Zhang, Linlin Shen, Xiaoling Luo, Zheng Lu, Zhuoqin Yang","submitted_at":"2024-08-15T11:34:05Z","abstract_excerpt":"The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. However, the recently proposed Kolmogorov-Arnold Network (KAN), based on nonlinear additive connections, has been proven to achieve performance comparable to MLPs with significantly fewer parameters. Despite this potential, the use of a single activation function space results in reduced performance of KAN and related works across different tasks. To address this issue, we propose an activation space Selectable KAN (S-K"},"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":"2408.08338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T11:34:05Z","cross_cats_sorted":[],"title_canon_sha256":"a68eb563dfc3e9677a81ee5f03d1e8312b5578c55fc77b615eefc8f78541eff6","abstract_canon_sha256":"f077fad1fbef38a71e4719e553ca59a43808dd546bc9bb0044bf71929664bbd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:52.802793Z","signature_b64":"eLqzvwv8SMj+70JocKoFrLvYznfnnqb2v/Td3PALmE5DhSAzMtra/yKGz/6pqSjdRblpeL+to4VvOtn68FbyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9e66352d1d654db666f8b76136c66022411e4bf4824b398e767cf661917a5f","last_reissued_at":"2026-07-05T08:55:52.802379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:52.802379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation Space Selectable Kolmogorov-Arnold Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiansong Zhang, Linlin Shen, Xiaoling Luo, Zheng Lu, Zhuoqin Yang","submitted_at":"2024-08-15T11:34:05Z","abstract_excerpt":"The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. However, the recently proposed Kolmogorov-Arnold Network (KAN), based on nonlinear additive connections, has been proven to achieve performance comparable to MLPs with significantly fewer parameters. Despite this potential, the use of a single activation function space results in reduced performance of KAN and related works across different tasks. To address this issue, we propose an activation space Selectable KAN (S-K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08338","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/2408.08338/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":"2408.08338","created_at":"2026-07-05T08:55:52.802440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08338v1","created_at":"2026-07-05T08:55:52.802440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08338","created_at":"2026-07-05T08:55:52.802440+00:00"},{"alias_kind":"pith_short_12","alias_value":"76PGMNJNDVSU","created_at":"2026-07-05T08:55:52.802440+00:00"},{"alias_kind":"pith_short_16","alias_value":"76PGMNJNDVSU3NTG","created_at":"2026-07-05T08:55:52.802440+00:00"},{"alias_kind":"pith_short_8","alias_value":"76PGMNJN","created_at":"2026-07-05T08:55:52.802440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA","json":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA.json","graph_json":"https://pith.science/api/pith-number/76PGMNJNDVSU3NTG7C3WCNWGMA/graph.json","events_json":"https://pith.science/api/pith-number/76PGMNJNDVSU3NTG7C3WCNWGMA/events.json","paper":"https://pith.science/paper/76PGMNJN"},"agent_actions":{"view_html":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA","download_json":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA.json","view_paper":"https://pith.science/paper/76PGMNJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08338&json=true","fetch_graph":"https://pith.science/api/pith-number/76PGMNJNDVSU3NTG7C3WCNWGMA/graph.json","fetch_events":"https://pith.science/api/pith-number/76PGMNJNDVSU3NTG7C3WCNWGMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA/action/storage_attestation","attest_author":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA/action/author_attestation","sign_citation":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA/action/citation_signature","submit_replication":"https://pith.science/pith/76PGMNJNDVSU3NTG7C3WCNWGMA/action/replication_record"}},"created_at":"2026-07-05T08:55:52.802440+00:00","updated_at":"2026-07-05T08:55:52.802440+00:00"}