{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7F6L6SCXWIKBWDTXZ4JXZNW4KA","short_pith_number":"pith:7F6L6SCX","schema_version":"1.0","canonical_sha256":"f97cbf4857b2141b0e77cf137cb6dc502a7744960d3fc26c9b98cfb6d17a231a","source":{"kind":"arxiv","id":"2210.07606","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Heterophily For Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chenqing Hua, Doina Precup, Jiaqi Zhu, Mingde Zhao, Qincheng Lu, Shuyuan Zhang, Sitao Luan, Xiao-Wen Chang","submitted_at":"2022-10-14T08:00:26Z","abstract_excerpt":"Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been commonly believed to outperform NNs in real-world tasks, recent work has identified a non-trivial set of datasets where their performance compared to NNs is not satisfactory. Heterophily has been considered the main cause of this empirical observation and numerous works have been put forward to address it. In this paper, we first revisit the widely used homophily metrics and point out that their consideration of only graph"},"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":"2210.07606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-14T08:00:26Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"f78f41fdaa8dae8f51af3ab04fa238e026ce5f3091e0f1c0a53e8765bcce8c82","abstract_canon_sha256":"27246d8a83b21045b15d90ee565a07ca8f80f007cfc2ac8367b6df5b7792c0d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:39.205608Z","signature_b64":"5nbODVOo02WHGOoILqh1gE9NskCYfKmQnYiRYX/aVY0bYS2hE29PgS68O+rJS2bxXHH9zATPoRqQPZItXLwoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f97cbf4857b2141b0e77cf137cb6dc502a7744960d3fc26c9b98cfb6d17a231a","last_reissued_at":"2026-07-05T05:06:39.205190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:39.205190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Heterophily For Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chenqing Hua, Doina Precup, Jiaqi Zhu, Mingde Zhao, Qincheng Lu, Shuyuan Zhang, Sitao Luan, Xiao-Wen Chang","submitted_at":"2022-10-14T08:00:26Z","abstract_excerpt":"Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been commonly believed to outperform NNs in real-world tasks, recent work has identified a non-trivial set of datasets where their performance compared to NNs is not satisfactory. Heterophily has been considered the main cause of this empirical observation and numerous works have been put forward to address it. In this paper, we first revisit the widely used homophily metrics and point out that their consideration of only graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07606","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/2210.07606/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":"2210.07606","created_at":"2026-07-05T05:06:39.205244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07606v1","created_at":"2026-07-05T05:06:39.205244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07606","created_at":"2026-07-05T05:06:39.205244+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F6L6SCXWIKB","created_at":"2026-07-05T05:06:39.205244+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F6L6SCXWIKBWDTX","created_at":"2026-07-05T05:06:39.205244+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F6L6SCX","created_at":"2026-07-05T05:06:39.205244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA","json":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA.json","graph_json":"https://pith.science/api/pith-number/7F6L6SCXWIKBWDTXZ4JXZNW4KA/graph.json","events_json":"https://pith.science/api/pith-number/7F6L6SCXWIKBWDTXZ4JXZNW4KA/events.json","paper":"https://pith.science/paper/7F6L6SCX"},"agent_actions":{"view_html":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA","download_json":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA.json","view_paper":"https://pith.science/paper/7F6L6SCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07606&json=true","fetch_graph":"https://pith.science/api/pith-number/7F6L6SCXWIKBWDTXZ4JXZNW4KA/graph.json","fetch_events":"https://pith.science/api/pith-number/7F6L6SCXWIKBWDTXZ4JXZNW4KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA/action/storage_attestation","attest_author":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA/action/author_attestation","sign_citation":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA/action/citation_signature","submit_replication":"https://pith.science/pith/7F6L6SCXWIKBWDTXZ4JXZNW4KA/action/replication_record"}},"created_at":"2026-07-05T05:06:39.205244+00:00","updated_at":"2026-07-05T05:06:39.205244+00:00"}