{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3DPO2KKRJJUL3WQJ3LFAFG3RV2","short_pith_number":"pith:3DPO2KKR","schema_version":"1.0","canonical_sha256":"d8deed29514a68bdda09daca029b71ae9c7504aee753f5cf30dacbbf67b8f51a","source":{"kind":"arxiv","id":"2009.11469","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongwei Zhang, Tijin Yan, Yuanqing Xia, Yuan Zhang, Zenjun Xie","submitted_at":"2020-09-24T03:36:43Z","abstract_excerpt":"Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on this observation and develop novel insights towards the deeper GCN. First, we interpret the current graph convolutional operations from an optimization perspective and argue that over-smoothing is mainly caused by the naive first-order approximation of the solution to the optimization problem. Subsequently, we introduce two metrics to measure the over-smoothing on node-level tas"},"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":"2009.11469","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-24T03:36:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ad7238cdec254bcbd168e64a875a1a281917e40cc261d1f613a3153ce4b2d996","abstract_canon_sha256":"589ee603aad1d96dcb412890fb187b45d3aebca5b0856e21578eb2edbe5a9bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:56.918534Z","signature_b64":"DY1JFIpRzgfYSwYvU5tgolL8p4yhnsXX7gyWu6CLzItrmXG1rJwWeUuWL5KNjbksLc8PzBl6b3qL2zvI2xMOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8deed29514a68bdda09daca029b71ae9c7504aee753f5cf30dacbbf67b8f51a","last_reissued_at":"2026-07-05T01:37:56.918091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:56.918091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongwei Zhang, Tijin Yan, Yuanqing Xia, Yuan Zhang, Zenjun Xie","submitted_at":"2020-09-24T03:36:43Z","abstract_excerpt":"Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on this observation and develop novel insights towards the deeper GCN. First, we interpret the current graph convolutional operations from an optimization perspective and argue that over-smoothing is mainly caused by the naive first-order approximation of the solution to the optimization problem. Subsequently, we introduce two metrics to measure the over-smoothing on node-level tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11469","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/2009.11469/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":"2009.11469","created_at":"2026-07-05T01:37:56.918172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.11469v2","created_at":"2026-07-05T01:37:56.918172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11469","created_at":"2026-07-05T01:37:56.918172+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DPO2KKRJJUL","created_at":"2026-07-05T01:37:56.918172+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DPO2KKRJJUL3WQJ","created_at":"2026-07-05T01:37:56.918172+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DPO2KKR","created_at":"2026-07-05T01:37:56.918172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16790","citing_title":"Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective","ref_index":134,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2","json":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2.json","graph_json":"https://pith.science/api/pith-number/3DPO2KKRJJUL3WQJ3LFAFG3RV2/graph.json","events_json":"https://pith.science/api/pith-number/3DPO2KKRJJUL3WQJ3LFAFG3RV2/events.json","paper":"https://pith.science/paper/3DPO2KKR"},"agent_actions":{"view_html":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2","download_json":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2.json","view_paper":"https://pith.science/paper/3DPO2KKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.11469&json=true","fetch_graph":"https://pith.science/api/pith-number/3DPO2KKRJJUL3WQJ3LFAFG3RV2/graph.json","fetch_events":"https://pith.science/api/pith-number/3DPO2KKRJJUL3WQJ3LFAFG3RV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2/action/storage_attestation","attest_author":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2/action/author_attestation","sign_citation":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2/action/citation_signature","submit_replication":"https://pith.science/pith/3DPO2KKRJJUL3WQJ3LFAFG3RV2/action/replication_record"}},"created_at":"2026-07-05T01:37:56.918172+00:00","updated_at":"2026-07-05T01:37:56.918172+00:00"}