{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XSMAG6UIUH5356UGY3EFETBGLA","short_pith_number":"pith:XSMAG6UI","schema_version":"1.0","canonical_sha256":"bc98037a88a1fbbefa86c6c8524c26582c1ddc4138c2fe9dd385c27b165ac5a7","source":{"kind":"arxiv","id":"2003.04078","version":4},"attestation_state":"computed","paper":{"title":"A Survey on The Expressive Power of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ryoma Sato","submitted_at":"2020-03-09T12:37:40Z","abstract_excerpt":"Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs."},"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":"2003.04078","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-09T12:37:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"032f82c61179f7b2f417cabaaea5a17a9dd414dda60bb0358039e58d54d40b3f","abstract_canon_sha256":"507160366b7a839fc7febb976d0d8e36f2d30a3039889932d3cc5a1a803a61c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:24.716179Z","signature_b64":"N0b71ZqHdFz9H1PKMAzi2i5kQbgupB0ERQ7F61nuK5l1HwujV2zphwN7bLLdz3Nhv4Y6t/QwAbi/dXXRjvveCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc98037a88a1fbbefa86c6c8524c26582c1ddc4138c2fe9dd385c27b165ac5a7","last_reissued_at":"2026-07-05T01:43:24.715691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:24.715691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on The Expressive Power of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ryoma Sato","submitted_at":"2020-03-09T12:37:40Z","abstract_excerpt":"Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04078","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/2003.04078/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":"2003.04078","created_at":"2026-07-05T01:43:24.715748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04078v4","created_at":"2026-07-05T01:43:24.715748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04078","created_at":"2026-07-05T01:43:24.715748+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSMAG6UIUH53","created_at":"2026-07-05T01:43:24.715748+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSMAG6UIUH5356UG","created_at":"2026-07-05T01:43:24.715748+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSMAG6UI","created_at":"2026-07-05T01:43:24.715748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23467","citing_title":"S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08835","citing_title":"Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07669","citing_title":"Universal Spin Models are Universal Approximators in Machine Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA","json":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA.json","graph_json":"https://pith.science/api/pith-number/XSMAG6UIUH5356UGY3EFETBGLA/graph.json","events_json":"https://pith.science/api/pith-number/XSMAG6UIUH5356UGY3EFETBGLA/events.json","paper":"https://pith.science/paper/XSMAG6UI"},"agent_actions":{"view_html":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA","download_json":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA.json","view_paper":"https://pith.science/paper/XSMAG6UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04078&json=true","fetch_graph":"https://pith.science/api/pith-number/XSMAG6UIUH5356UGY3EFETBGLA/graph.json","fetch_events":"https://pith.science/api/pith-number/XSMAG6UIUH5356UGY3EFETBGLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA/action/storage_attestation","attest_author":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA/action/author_attestation","sign_citation":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA/action/citation_signature","submit_replication":"https://pith.science/pith/XSMAG6UIUH5356UGY3EFETBGLA/action/replication_record"}},"created_at":"2026-07-05T01:43:24.715748+00:00","updated_at":"2026-07-05T01:43:24.715748+00:00"}