{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M662H3ANP3SMPDPNNJT4BAZCLZ","short_pith_number":"pith:M662H3AN","schema_version":"1.0","canonical_sha256":"67bda3ec0d7ee4c78ded6a67c083225e4778320a9fc6596319fa102186c29f22","source":{"kind":"arxiv","id":"2306.14340","version":1},"attestation_state":"computed","paper":{"title":"GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophily","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Dawei Zhou, Haohui Wang, Shuaicheng Zhang, Si Zhang","submitted_at":"2023-06-25T20:57:35Z","abstract_excerpt":"While graph heterophily has been extensively studied in recent years, a fundamental research question largely remains nascent: How and to what extent will graph heterophily affect the prediction performance of graph neural networks (GNNs)? In this paper, we aim to demystify the impact of graph heterophily on GNN spectral filters. Our theoretical results show that it is essential to design adaptive polynomial filters that adapts different degrees of graph heterophily to guarantee the generalization performance of GNNs. Inspired by our theoretical findings, we propose a simple yet powerful GNN n"},"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":"2306.14340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T20:57:35Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"2bf387e8062ddbca5c92c77f516404d16f05cdb683390476d25168e10e22138b","abstract_canon_sha256":"f7e33e4485a52d04d9f667800dc289912f6cbad0772eed5a480c16538bf7abd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:35.069180Z","signature_b64":"YgWfIXR0zGmcYhoEusMJIhZOBD+qZ3fHuyiEv+TL/UimBpyQWrCFiJH2WjbPERc0gBPqzi8TinSrSeaEcN+YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67bda3ec0d7ee4c78ded6a67c083225e4778320a9fc6596319fa102186c29f22","last_reissued_at":"2026-07-05T06:24:35.068709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:35.068709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophily","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Dawei Zhou, Haohui Wang, Shuaicheng Zhang, Si Zhang","submitted_at":"2023-06-25T20:57:35Z","abstract_excerpt":"While graph heterophily has been extensively studied in recent years, a fundamental research question largely remains nascent: How and to what extent will graph heterophily affect the prediction performance of graph neural networks (GNNs)? In this paper, we aim to demystify the impact of graph heterophily on GNN spectral filters. Our theoretical results show that it is essential to design adaptive polynomial filters that adapts different degrees of graph heterophily to guarantee the generalization performance of GNNs. Inspired by our theoretical findings, we propose a simple yet powerful GNN n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14340","kind":"arxiv","version":1},"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/2306.14340/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":"2306.14340","created_at":"2026-07-05T06:24:35.068766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14340v1","created_at":"2026-07-05T06:24:35.068766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14340","created_at":"2026-07-05T06:24:35.068766+00:00"},{"alias_kind":"pith_short_12","alias_value":"M662H3ANP3SM","created_at":"2026-07-05T06:24:35.068766+00:00"},{"alias_kind":"pith_short_16","alias_value":"M662H3ANP3SMPDPN","created_at":"2026-07-05T06:24:35.068766+00:00"},{"alias_kind":"pith_short_8","alias_value":"M662H3AN","created_at":"2026-07-05T06:24:35.068766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17667","citing_title":"Handling Feature Heterogeneity with Learnable Graph Patches","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ","json":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ.json","graph_json":"https://pith.science/api/pith-number/M662H3ANP3SMPDPNNJT4BAZCLZ/graph.json","events_json":"https://pith.science/api/pith-number/M662H3ANP3SMPDPNNJT4BAZCLZ/events.json","paper":"https://pith.science/paper/M662H3AN"},"agent_actions":{"view_html":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ","download_json":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ.json","view_paper":"https://pith.science/paper/M662H3AN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14340&json=true","fetch_graph":"https://pith.science/api/pith-number/M662H3ANP3SMPDPNNJT4BAZCLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/M662H3ANP3SMPDPNNJT4BAZCLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ/action/storage_attestation","attest_author":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ/action/author_attestation","sign_citation":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ/action/citation_signature","submit_replication":"https://pith.science/pith/M662H3ANP3SMPDPNNJT4BAZCLZ/action/replication_record"}},"created_at":"2026-07-05T06:24:35.068766+00:00","updated_at":"2026-07-05T06:24:35.068766+00:00"}