{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UOLKVVBHVHHYQ4FVVNJXPDDIRN","short_pith_number":"pith:UOLKVVBH","schema_version":"1.0","canonical_sha256":"a396aad427a9cf8870b5ab53778c688b4151154cd9fe64719796d3386acdb82f","source":{"kind":"arxiv","id":"2406.18354","version":2},"attestation_state":"computed","paper":{"title":"Kolmogorov-Arnold Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Mastropietro, Aris Anagnostopoulos, Gianluca De Carlo","submitted_at":"2024-06-26T13:54:59Z","abstract_excerpt":"Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inhere"},"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":"2406.18354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T13:54:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7dbc0f20fd7e111ccd1a15df429f263d818e784ed3d02704f1085e4b9118ba31","abstract_canon_sha256":"41e62d76610f6a0e150b058507e0a999a2c102a79e356253318290516f41bf6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:18.347154Z","signature_b64":"4eaT4ePt/fWpuHJDEemn5vQtvHQRa5PGip1VdFypcO+hUIySwn2i33NtDUyoc25eWkfX8UcLdEFRPMEZO8R9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a396aad427a9cf8870b5ab53778c688b4151154cd9fe64719796d3386acdb82f","last_reissued_at":"2026-07-05T11:12:18.346591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:18.346591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kolmogorov-Arnold Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Mastropietro, Aris Anagnostopoulos, Gianluca De Carlo","submitted_at":"2024-06-26T13:54:59Z","abstract_excerpt":"Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inhere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18354","kind":"arxiv","version":2},"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/2406.18354/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":"2406.18354","created_at":"2026-07-05T11:12:18.346654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18354v2","created_at":"2026-07-05T11:12:18.346654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18354","created_at":"2026-07-05T11:12:18.346654+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOLKVVBHVHHY","created_at":"2026-07-05T11:12:18.346654+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOLKVVBHVHHYQ4FV","created_at":"2026-07-05T11:12:18.346654+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOLKVVBH","created_at":"2026-07-05T11:12:18.346654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04435","citing_title":"QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23383","citing_title":"Automated Modeling Method for Pathloss Model Discovery","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02466","citing_title":"Variational Kolmogorov-Arnold Network","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09572","citing_title":"KAN Text to Vision? The Exploration of Kolmogorov-Arnold Networks for Multi-Scale Sequence-Based Pose Animation from Sign Language Notation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN","json":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN.json","graph_json":"https://pith.science/api/pith-number/UOLKVVBHVHHYQ4FVVNJXPDDIRN/graph.json","events_json":"https://pith.science/api/pith-number/UOLKVVBHVHHYQ4FVVNJXPDDIRN/events.json","paper":"https://pith.science/paper/UOLKVVBH"},"agent_actions":{"view_html":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN","download_json":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN.json","view_paper":"https://pith.science/paper/UOLKVVBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18354&json=true","fetch_graph":"https://pith.science/api/pith-number/UOLKVVBHVHHYQ4FVVNJXPDDIRN/graph.json","fetch_events":"https://pith.science/api/pith-number/UOLKVVBHVHHYQ4FVVNJXPDDIRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN/action/storage_attestation","attest_author":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN/action/author_attestation","sign_citation":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN/action/citation_signature","submit_replication":"https://pith.science/pith/UOLKVVBHVHHYQ4FVVNJXPDDIRN/action/replication_record"}},"created_at":"2026-07-05T11:12:18.346654+00:00","updated_at":"2026-07-05T11:12:18.346654+00:00"}