{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IKDFQTCXKWMNZEFZRFDNL6EEVO","short_pith_number":"pith:IKDFQTCX","schema_version":"1.0","canonical_sha256":"4286584c575598dc90b98946d5f884abbd5f258b85f7f5a3716ffa2f6838a776","source":{"kind":"arxiv","id":"2406.18380","version":4},"attestation_state":"computed","paper":{"title":"KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Panagopoulos, Giannis Nikolentzos, Jun Pang, Michail Chatzianastasis, Michalis Vazirgiannis, Roman Bresson","submitted_at":"2024-06-26T14:21:21Z","abstract_excerpt":"In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. Most GNNs typically consist of a sequence of neighborhood aggregation (a.k.a., message-passing) layers, within which the representation of each node is updated based on those of its neighbors. The most expressive message-passing GNNs can be obtained through the use of the sum aggregator and of MLPs for feature transformation, thanks to their universal approximation capabilities. However, the limitations of MLPs recently motivated the introduction of another family of univers"},"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":"2406.18380","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T14:21:21Z","cross_cats_sorted":[],"title_canon_sha256":"2f6e5a30820e4c8392cf88561bf2615fd3edcf8d254b5c191424ba56c06d0753","abstract_canon_sha256":"44cc5d121d08573b86b26f8f260504d40a00e269570f32687cc327a1fdb34007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:07.745928Z","signature_b64":"SAmU8Jdsusut50Z8BEIbDl4oq4LLQLRJ2ZG+KT9qs5kePt1meqXAQ1u+6D6S7jizq+KpMlZyFoL4gHRGH5JfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4286584c575598dc90b98946d5f884abbd5f258b85f7f5a3716ffa2f6838a776","last_reissued_at":"2026-07-05T10:25:07.745405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:07.745405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Panagopoulos, Giannis Nikolentzos, Jun Pang, Michail Chatzianastasis, Michalis Vazirgiannis, Roman Bresson","submitted_at":"2024-06-26T14:21:21Z","abstract_excerpt":"In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. Most GNNs typically consist of a sequence of neighborhood aggregation (a.k.a., message-passing) layers, within which the representation of each node is updated based on those of its neighbors. The most expressive message-passing GNNs can be obtained through the use of the sum aggregator and of MLPs for feature transformation, thanks to their universal approximation capabilities. However, the limitations of MLPs recently motivated the introduction of another family of univers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18380","kind":"arxiv","version":4},"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/2406.18380/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":"2406.18380","created_at":"2026-07-05T10:25:07.745473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18380v4","created_at":"2026-07-05T10:25:07.745473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18380","created_at":"2026-07-05T10:25:07.745473+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKDFQTCXKWMN","created_at":"2026-07-05T10:25:07.745473+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKDFQTCXKWMNZEFZ","created_at":"2026-07-05T10:25:07.745473+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKDFQTCX","created_at":"2026-07-05T10:25:07.745473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28459","citing_title":"scKDGM: KAN-guided Dynamic Graph Masked Learning for Single-Cell RNA-seq Clustering","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2501.04757","citing_title":"Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty","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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16586","citing_title":"A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO","json":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO.json","graph_json":"https://pith.science/api/pith-number/IKDFQTCXKWMNZEFZRFDNL6EEVO/graph.json","events_json":"https://pith.science/api/pith-number/IKDFQTCXKWMNZEFZRFDNL6EEVO/events.json","paper":"https://pith.science/paper/IKDFQTCX"},"agent_actions":{"view_html":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO","download_json":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO.json","view_paper":"https://pith.science/paper/IKDFQTCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18380&json=true","fetch_graph":"https://pith.science/api/pith-number/IKDFQTCXKWMNZEFZRFDNL6EEVO/graph.json","fetch_events":"https://pith.science/api/pith-number/IKDFQTCXKWMNZEFZRFDNL6EEVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO/action/storage_attestation","attest_author":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO/action/author_attestation","sign_citation":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO/action/citation_signature","submit_replication":"https://pith.science/pith/IKDFQTCXKWMNZEFZRFDNL6EEVO/action/replication_record"}},"created_at":"2026-07-05T10:25:07.745473+00:00","updated_at":"2026-07-05T10:25:07.745473+00:00"}