{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XCGF2I54AVY4KY6IQHKKBQHPTF","short_pith_number":"pith:XCGF2I54","schema_version":"1.0","canonical_sha256":"b88c5d23bc0571c563c881d4a0c0ef9968131d0675e576be9a44604ae02f8262","source":{"kind":"arxiv","id":"2205.11172","version":2},"attestation_state":"computed","paper":{"title":"How Powerful are Spectral Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Muhan Zhang, Xiyuan Wang","submitted_at":"2022-05-23T10:22:12Z","abstract_excerpt":"Spectral Graph Neural Network is a kind of Graph Neural Network (GNN) based on graph signal filters. Some models able to learn arbitrary spectral filters have emerged recently. However, few works analyze the expressive power of spectral GNNs. This paper studies spectral GNNs' expressive power theoretically. We first prove that even spectral GNNs without nonlinearity can produce arbitrary graph signals and give two conditions for reaching universality. They are: 1) no multiple eigenvalues of graph Laplacian, and 2) no missing frequency components in node features. We also establish a connection"},"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":"2205.11172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T10:22:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be8e4b161ed58591ce440bc010f5dadb34d142db5448e5cf69d8a9ee9e44dd5d","abstract_canon_sha256":"c764ede6cee168cacbd76dcf2e34c5f156746eb96cb534dde7d763a4413222a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:40.765544Z","signature_b64":"158pjVdTZaDjY2QG9q4b+fZXuxiUR4Hca4T+Pulxs+3mMBfZnLE+4a5ELnNP646VjbkHPxSzUbPcvOii34q/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b88c5d23bc0571c563c881d4a0c0ef9968131d0675e576be9a44604ae02f8262","last_reissued_at":"2026-07-05T04:32:40.765053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:40.765053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Powerful are Spectral Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Muhan Zhang, Xiyuan Wang","submitted_at":"2022-05-23T10:22:12Z","abstract_excerpt":"Spectral Graph Neural Network is a kind of Graph Neural Network (GNN) based on graph signal filters. Some models able to learn arbitrary spectral filters have emerged recently. However, few works analyze the expressive power of spectral GNNs. This paper studies spectral GNNs' expressive power theoretically. We first prove that even spectral GNNs without nonlinearity can produce arbitrary graph signals and give two conditions for reaching universality. They are: 1) no multiple eigenvalues of graph Laplacian, and 2) no missing frequency components in node features. We also establish a connection"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11172","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/2205.11172/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":"2205.11172","created_at":"2026-07-05T04:32:40.765110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11172v2","created_at":"2026-07-05T04:32:40.765110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11172","created_at":"2026-07-05T04:32:40.765110+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCGF2I54AVY4","created_at":"2026-07-05T04:32:40.765110+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCGF2I54AVY4KY6I","created_at":"2026-07-05T04:32:40.765110+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCGF2I54","created_at":"2026-07-05T04:32:40.765110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.04838","citing_title":"SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF","json":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF.json","graph_json":"https://pith.science/api/pith-number/XCGF2I54AVY4KY6IQHKKBQHPTF/graph.json","events_json":"https://pith.science/api/pith-number/XCGF2I54AVY4KY6IQHKKBQHPTF/events.json","paper":"https://pith.science/paper/XCGF2I54"},"agent_actions":{"view_html":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF","download_json":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF.json","view_paper":"https://pith.science/paper/XCGF2I54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11172&json=true","fetch_graph":"https://pith.science/api/pith-number/XCGF2I54AVY4KY6IQHKKBQHPTF/graph.json","fetch_events":"https://pith.science/api/pith-number/XCGF2I54AVY4KY6IQHKKBQHPTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF/action/storage_attestation","attest_author":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF/action/author_attestation","sign_citation":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF/action/citation_signature","submit_replication":"https://pith.science/pith/XCGF2I54AVY4KY6IQHKKBQHPTF/action/replication_record"}},"created_at":"2026-07-05T04:32:40.765110+00:00","updated_at":"2026-07-05T04:32:40.765110+00:00"}