{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ESO76P55KE2LRMH37YKGVXGX3T","short_pith_number":"pith:ESO76P55","schema_version":"1.0","canonical_sha256":"249dff3fbd5134b8b0fbfe146adcd7dcde7d42809d39760ecd917a63d41f3f2d","source":{"kind":"arxiv","id":"2306.01323","version":3},"attestation_state":"computed","paper":{"title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haitao Mao, Haoyu Han, Jiliang Tang, Neil Shah, Tong Zhao, Wei Jin, Yao Ma, Zhikai Chen","submitted_at":"2023-06-02T07:46:20Z","abstract_excerpt":"Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity. However, the analysis of GNN performance with respect to nodes exhibiting different structural patterns, e.g., homophilic nodes in heterophilic graphs, remains rather limited. In the present study, we p"},"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":"2306.01323","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T07:46:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59d2d7d1364d5b4e81565d8e91453117d48f3680539a70f7a0a8cfebda2737cf","abstract_canon_sha256":"7b4fe6efacaa527a18d14f2430dca3777e51b43ac14bb06eafa4df1574962277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:02.320576Z","signature_b64":"+Jti+d1jS4OlFncHzwWWdTx9HtvyVV3SlOPr5ZzacJEG2HS6U33N8kAncdR2VIHJRWt2MvippHe7uWLMRW2qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"249dff3fbd5134b8b0fbfe146adcd7dcde7d42809d39760ecd917a63d41f3f2d","last_reissued_at":"2026-07-05T07:01:02.319962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:02.319962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haitao Mao, Haoyu Han, Jiliang Tang, Neil Shah, Tong Zhao, Wei Jin, Yao Ma, Zhikai Chen","submitted_at":"2023-06-02T07:46:20Z","abstract_excerpt":"Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity. However, the analysis of GNN performance with respect to nodes exhibiting different structural patterns, e.g., homophilic nodes in heterophilic graphs, remains rather limited. In the present study, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01323","kind":"arxiv","version":3},"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/2306.01323/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":"2306.01323","created_at":"2026-07-05T07:01:02.320050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01323v3","created_at":"2026-07-05T07:01:02.320050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01323","created_at":"2026-07-05T07:01:02.320050+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESO76P55KE2L","created_at":"2026-07-05T07:01:02.320050+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESO76P55KE2LRMH3","created_at":"2026-07-05T07:01:02.320050+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESO76P55","created_at":"2026-07-05T07:01:02.320050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03033","citing_title":"Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T","json":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T.json","graph_json":"https://pith.science/api/pith-number/ESO76P55KE2LRMH37YKGVXGX3T/graph.json","events_json":"https://pith.science/api/pith-number/ESO76P55KE2LRMH37YKGVXGX3T/events.json","paper":"https://pith.science/paper/ESO76P55"},"agent_actions":{"view_html":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T","download_json":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T.json","view_paper":"https://pith.science/paper/ESO76P55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01323&json=true","fetch_graph":"https://pith.science/api/pith-number/ESO76P55KE2LRMH37YKGVXGX3T/graph.json","fetch_events":"https://pith.science/api/pith-number/ESO76P55KE2LRMH37YKGVXGX3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T/action/storage_attestation","attest_author":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T/action/author_attestation","sign_citation":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T/action/citation_signature","submit_replication":"https://pith.science/pith/ESO76P55KE2LRMH37YKGVXGX3T/action/replication_record"}},"created_at":"2026-07-05T07:01:02.320050+00:00","updated_at":"2026-07-05T07:01:02.320050+00:00"}