{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JZLZOHI55JUAR4C554EBDCVOZI","short_pith_number":"pith:JZLZOHI5","schema_version":"1.0","canonical_sha256":"4e57971d1dea6808f05def08118aaeca276d42553da9de0c61c709e867644226","source":{"kind":"arxiv","id":"2308.08235","version":2},"attestation_state":"computed","paper":{"title":"The Expressive Power of Graph Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Bingxu Zhang, Changjun Fan, Jincai Huang, Kuihua Huang, Shixuan Liu, Xiang Zhao, Zhong Liu","submitted_at":"2023-08-16T09:12:21Z","abstract_excerpt":"Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories compreh"},"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":"2308.08235","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-16T09:12:21Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"813c57fce6da3aadccd6a178b57a764a988731dd54614ab1245b8cbd58843a19","abstract_canon_sha256":"ab5e8bc1ffb24c7d28b0777f89b6e4505e366473e69170730428b18c9442aa27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:12.453883Z","signature_b64":"a+jfVw2Y0wT+HR6xPzTM3S6LeMKUV8O9NlLzPK+Waxh00v/53czSTszd0HgCRi9vNIeqTVURAlhX5WH3d9JtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e57971d1dea6808f05def08118aaeca276d42553da9de0c61c709e867644226","last_reissued_at":"2026-07-05T09:59:12.453411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:12.453411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Expressive Power of Graph Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Bingxu Zhang, Changjun Fan, Jincai Huang, Kuihua Huang, Shixuan Liu, Xiang Zhao, Zhong Liu","submitted_at":"2023-08-16T09:12:21Z","abstract_excerpt":"Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08235","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/2308.08235/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":"2308.08235","created_at":"2026-07-05T09:59:12.453483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08235v2","created_at":"2026-07-05T09:59:12.453483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08235","created_at":"2026-07-05T09:59:12.453483+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZLZOHI55JUA","created_at":"2026-07-05T09:59:12.453483+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZLZOHI55JUAR4C5","created_at":"2026-07-05T09:59:12.453483+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZLZOHI5","created_at":"2026-07-05T09:59:12.453483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14338","citing_title":"On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI","json":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI.json","graph_json":"https://pith.science/api/pith-number/JZLZOHI55JUAR4C554EBDCVOZI/graph.json","events_json":"https://pith.science/api/pith-number/JZLZOHI55JUAR4C554EBDCVOZI/events.json","paper":"https://pith.science/paper/JZLZOHI5"},"agent_actions":{"view_html":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI","download_json":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI.json","view_paper":"https://pith.science/paper/JZLZOHI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08235&json=true","fetch_graph":"https://pith.science/api/pith-number/JZLZOHI55JUAR4C554EBDCVOZI/graph.json","fetch_events":"https://pith.science/api/pith-number/JZLZOHI55JUAR4C554EBDCVOZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI/action/storage_attestation","attest_author":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI/action/author_attestation","sign_citation":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI/action/citation_signature","submit_replication":"https://pith.science/pith/JZLZOHI55JUAR4C554EBDCVOZI/action/replication_record"}},"created_at":"2026-07-05T09:59:12.453483+00:00","updated_at":"2026-07-05T09:59:12.453483+00:00"}