{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N2LBNLVPT64RQKOGLQWHFZVIYU","short_pith_number":"pith:N2LBNLVP","schema_version":"1.0","canonical_sha256":"6e9616aeaf9fb91829c65c2c72e6a8c5105dadb917008acf30c87889251a1e25","source":{"kind":"arxiv","id":"2112.11628","version":4},"attestation_state":"computed","paper":{"title":"SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baosheng Yu, Binbin Lin, Dacheng Tao, Liu Liu, Weigang Lu, Wei Zhao, Yaming Yang, Yibing Zhan, Ziyu Guan","submitted_at":"2021-12-22T02:18:31Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs. On the other hand, existing anti-over-smoothing methods all perform full convolutions up to the model depth. They could not well resist "},"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":"2112.11628","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"d92e0f85f8e6793c9d418d84ebd5d342dc96e3f5e6611eb79ccdb11e2934a076","abstract_canon_sha256":"3f286471f41523dbff22503db8bf238ec3cf5cd451945d5d9e00d250259f4c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:18.459183Z","signature_b64":"wI+V8Wvw3d21dJnKpYAI450i0RWzng7BTAXqqGfUv6UzbKrjCM3qDOdt4YFUhMvyllUBnqiME+vJBWPWXG8sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e9616aeaf9fb91829c65c2c72e6a8c5105dadb917008acf30c87889251a1e25","last_reissued_at":"2026-07-05T07:36:18.458682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:18.458682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baosheng Yu, Binbin Lin, Dacheng Tao, Liu Liu, Weigang Lu, Wei Zhao, Yaming Yang, Yibing Zhan, Ziyu Guan","submitted_at":"2021-12-22T02:18:31Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs. On the other hand, existing anti-over-smoothing methods all perform full convolutions up to the model depth. They could not well resist "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11628","kind":"arxiv","version":4},"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/2112.11628/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":"2112.11628","created_at":"2026-07-05T07:36:18.458742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11628v4","created_at":"2026-07-05T07:36:18.458742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11628","created_at":"2026-07-05T07:36:18.458742+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2LBNLVPT64R","created_at":"2026-07-05T07:36:18.458742+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2LBNLVPT64RQKOG","created_at":"2026-07-05T07:36:18.458742+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2LBNLVP","created_at":"2026-07-05T07:36:18.458742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08144","citing_title":"AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU","json":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU.json","graph_json":"https://pith.science/api/pith-number/N2LBNLVPT64RQKOGLQWHFZVIYU/graph.json","events_json":"https://pith.science/api/pith-number/N2LBNLVPT64RQKOGLQWHFZVIYU/events.json","paper":"https://pith.science/paper/N2LBNLVP"},"agent_actions":{"view_html":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU","download_json":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU.json","view_paper":"https://pith.science/paper/N2LBNLVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11628&json=true","fetch_graph":"https://pith.science/api/pith-number/N2LBNLVPT64RQKOGLQWHFZVIYU/graph.json","fetch_events":"https://pith.science/api/pith-number/N2LBNLVPT64RQKOGLQWHFZVIYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU/action/storage_attestation","attest_author":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU/action/author_attestation","sign_citation":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU/action/citation_signature","submit_replication":"https://pith.science/pith/N2LBNLVPT64RQKOGLQWHFZVIYU/action/replication_record"}},"created_at":"2026-07-05T07:36:18.458742+00:00","updated_at":"2026-07-05T07:36:18.458742+00:00"}