{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZWYIK2E7OUHV7YMHCE7Y2RN7IV","short_pith_number":"pith:ZWYIK2E7","schema_version":"1.0","canonical_sha256":"cdb085689f750f5fe187113f8d45bf4579c68f38f69b5ecf517f23878a31083b","source":{"kind":"arxiv","id":"2112.13507","version":2},"attestation_state":"computed","paper":{"title":"Block Modeling-Guided Graph Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chundong Liang, Dongxiao He, Huixin Liu, Mingxiang Wen, Pengfei Jiao, Zhiyong Feng","submitted_at":"2021-12-27T04:52:11Z","abstract_excerpt":"Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modeling into the framework of GCN so that it can realize \"block-guided classified aggregation\", and automatically learn the corresponding aggregation rules"},"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":"2112.13507","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T04:52:11Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"3210738064c843e73213c6e6cae4ef3ebf52d46be0e7551f94126210bd7e24ce","abstract_canon_sha256":"2f1d36f0eb5dad9d3b1a73425c151cbbd2458e537e24f4238399b5401580f07a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:16.240819Z","signature_b64":"dEKGsT7Fo9+krxo00cEstf2rXBUas+fhkSMOUSZ6Zc6mW7j0Cxr2/Jaewn6hFH+31scQCY7lAxHBKBSxCbIMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb085689f750f5fe187113f8d45bf4579c68f38f69b5ecf517f23878a31083b","last_reissued_at":"2026-07-05T03:44:16.240477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:16.240477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block Modeling-Guided Graph Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chundong Liang, Dongxiao He, Huixin Liu, Mingxiang Wen, Pengfei Jiao, Zhiyong Feng","submitted_at":"2021-12-27T04:52:11Z","abstract_excerpt":"Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modeling into the framework of GCN so that it can realize \"block-guided classified aggregation\", and automatically learn the corresponding aggregation rules"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13507","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/2112.13507/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":"2112.13507","created_at":"2026-07-05T03:44:16.240533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13507v2","created_at":"2026-07-05T03:44:16.240533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13507","created_at":"2026-07-05T03:44:16.240533+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWYIK2E7OUHV","created_at":"2026-07-05T03:44:16.240533+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWYIK2E7OUHV7YMH","created_at":"2026-07-05T03:44:16.240533+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWYIK2E7","created_at":"2026-07-05T03:44:16.240533+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/ZWYIK2E7OUHV7YMHCE7Y2RN7IV","json":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV.json","graph_json":"https://pith.science/api/pith-number/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/graph.json","events_json":"https://pith.science/api/pith-number/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/events.json","paper":"https://pith.science/paper/ZWYIK2E7"},"agent_actions":{"view_html":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV","download_json":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV.json","view_paper":"https://pith.science/paper/ZWYIK2E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13507&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/action/storage_attestation","attest_author":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/action/author_attestation","sign_citation":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/action/citation_signature","submit_replication":"https://pith.science/pith/ZWYIK2E7OUHV7YMHCE7Y2RN7IV/action/replication_record"}},"created_at":"2026-07-05T03:44:16.240533+00:00","updated_at":"2026-07-05T03:44:16.240533+00:00"}