{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:527MMDIQD5VKEG7VSCDDQEIA5X","short_pith_number":"pith:527MMDIQ","schema_version":"1.0","canonical_sha256":"eebec60d101f6aa21bf59086381100edc241a4c2376166d89db9e6697a6809af","source":{"kind":"arxiv","id":"2210.16508","version":2},"attestation_state":"computed","paper":{"title":"Clenshaw Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yuhe Guo, Zhewei Wei","submitted_at":"2022-10-29T06:32:39Z","abstract_excerpt":"Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations. Recent GCN models use various residual connection techniques to alleviate the model degradation problem such as over-smoothing and gradient vanishing. Existing residual connection techniques, however, fail to make extensive use of underlying graph structure as in the graph spectral domain, which is critical for obtaining satisfactory results on heterophilic graphs. In this paper, we introduce ClenshawGCN, a GNN model that employ"},"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":"2210.16508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-29T06:32:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ad81777de78a39b11070cd234352937842375573bec2b06fc5e022b5322eae7","abstract_canon_sha256":"5e575bd0e908d56af4ad810927dd59d58d5f668b76c8865b5658e783069c17e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:54.942959Z","signature_b64":"/8Hh005QDzdyygc/Oc8Eq1FjJfVS/QNhaTPeaytdTm5jbqFVf8io/OZyZ319jDWWI/HQYB2HKcpQh/jMDWq0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eebec60d101f6aa21bf59086381100edc241a4c2376166d89db9e6697a6809af","last_reissued_at":"2026-07-05T05:12:54.942420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:54.942420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clenshaw Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yuhe Guo, Zhewei Wei","submitted_at":"2022-10-29T06:32:39Z","abstract_excerpt":"Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations. Recent GCN models use various residual connection techniques to alleviate the model degradation problem such as over-smoothing and gradient vanishing. Existing residual connection techniques, however, fail to make extensive use of underlying graph structure as in the graph spectral domain, which is critical for obtaining satisfactory results on heterophilic graphs. In this paper, we introduce ClenshawGCN, a GNN model that employ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16508","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/2210.16508/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":"2210.16508","created_at":"2026-07-05T05:12:54.942491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16508v2","created_at":"2026-07-05T05:12:54.942491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16508","created_at":"2026-07-05T05:12:54.942491+00:00"},{"alias_kind":"pith_short_12","alias_value":"527MMDIQD5VK","created_at":"2026-07-05T05:12:54.942491+00:00"},{"alias_kind":"pith_short_16","alias_value":"527MMDIQD5VKEG7V","created_at":"2026-07-05T05:12:54.942491+00:00"},{"alias_kind":"pith_short_8","alias_value":"527MMDIQ","created_at":"2026-07-05T05:12:54.942491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.19820","citing_title":"Hierarchical Uncertainty-Aware Graph Neural Network","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X","json":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X.json","graph_json":"https://pith.science/api/pith-number/527MMDIQD5VKEG7VSCDDQEIA5X/graph.json","events_json":"https://pith.science/api/pith-number/527MMDIQD5VKEG7VSCDDQEIA5X/events.json","paper":"https://pith.science/paper/527MMDIQ"},"agent_actions":{"view_html":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X","download_json":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X.json","view_paper":"https://pith.science/paper/527MMDIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16508&json=true","fetch_graph":"https://pith.science/api/pith-number/527MMDIQD5VKEG7VSCDDQEIA5X/graph.json","fetch_events":"https://pith.science/api/pith-number/527MMDIQD5VKEG7VSCDDQEIA5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X/action/storage_attestation","attest_author":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X/action/author_attestation","sign_citation":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X/action/citation_signature","submit_replication":"https://pith.science/pith/527MMDIQD5VKEG7VSCDDQEIA5X/action/replication_record"}},"created_at":"2026-07-05T05:12:54.942491+00:00","updated_at":"2026-07-05T05:12:54.942491+00:00"}