{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ARVAFCVHQYHB4M57DKVQERZI3A","short_pith_number":"pith:ARVAFCVH","schema_version":"1.0","canonical_sha256":"046a028aa7860e1e33bf1aab024728d807353efd5180279657de04fdaf60a635","source":{"kind":"arxiv","id":"2410.08961","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Mendon\\c{c}a Sasse, Claudio Miceli de Farias","submitted_at":"2024-10-11T16:30:04Z","abstract_excerpt":"Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing t"},"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":"2410.08961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T16:30:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"855bb0cacbbcfb03d0c8fae7506e72ed8eb00d20b9a0044e9070162ecbeb1f18","abstract_canon_sha256":"0e26a8f8772d7d7762305c1fc775326f501efd0ebd8f6b714e7e33684cc4dfa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:20.149429Z","signature_b64":"VmSuVpzYbdsfVhBXB1qiUrkD6N6+rMbLHY5h7E+NoU/S8jqwFagIMf133x3GY2zL0Esvmv6wLBAkm3WPffLqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046a028aa7860e1e33bf1aab024728d807353efd5180279657de04fdaf60a635","last_reissued_at":"2026-07-05T09:19:20.149044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:20.149044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Mendon\\c{c}a Sasse, Claudio Miceli de Farias","submitted_at":"2024-10-11T16:30:04Z","abstract_excerpt":"Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08961","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/2410.08961/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":"2410.08961","created_at":"2026-07-05T09:19:20.149099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08961v1","created_at":"2026-07-05T09:19:20.149099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08961","created_at":"2026-07-05T09:19:20.149099+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARVAFCVHQYHB","created_at":"2026-07-05T09:19:20.149099+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARVAFCVHQYHB4M57","created_at":"2026-07-05T09:19:20.149099+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARVAFCVH","created_at":"2026-07-05T09:19:20.149099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07629","citing_title":"Enhancing Federated Learning with Kolmogorov-Arnold Networks: A Comparative Study Across Diverse Aggregation Strategies","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A","json":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A.json","graph_json":"https://pith.science/api/pith-number/ARVAFCVHQYHB4M57DKVQERZI3A/graph.json","events_json":"https://pith.science/api/pith-number/ARVAFCVHQYHB4M57DKVQERZI3A/events.json","paper":"https://pith.science/paper/ARVAFCVH"},"agent_actions":{"view_html":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A","download_json":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A.json","view_paper":"https://pith.science/paper/ARVAFCVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08961&json=true","fetch_graph":"https://pith.science/api/pith-number/ARVAFCVHQYHB4M57DKVQERZI3A/graph.json","fetch_events":"https://pith.science/api/pith-number/ARVAFCVHQYHB4M57DKVQERZI3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A/action/storage_attestation","attest_author":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A/action/author_attestation","sign_citation":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A/action/citation_signature","submit_replication":"https://pith.science/pith/ARVAFCVHQYHB4M57DKVQERZI3A/action/replication_record"}},"created_at":"2026-07-05T09:19:20.149099+00:00","updated_at":"2026-07-05T09:19:20.149099+00:00"}