{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LC3LKLSHYQQBBERJMXQKYWZEFG","short_pith_number":"pith:LC3LKLSH","schema_version":"1.0","canonical_sha256":"58b6b52e47c42010922965e0ac5b242991a4e6bcda7f96a8beea9949ddc822f8","source":{"kind":"arxiv","id":"2206.04361","version":1},"attestation_state":"computed","paper":{"title":"Model Degradation Hinders Deep Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Cui, Jun Gao, Wentao Zhang, Yikuan Xia, Yuezihan Jiang, Zeang Sheng, Zhi Yang, Ziqi Yin","submitted_at":"2022-06-09T09:02:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks.However, drastic performance degradation is always observed when a GNN is stacked with many layers. As a result, most GNNs only have shallow architectures, which limits their expressive power and exploitation of deep neighborhoods.Most recent studies attribute the performance degradation of deep GNNs to the \\textit{over-smoothing} issue. In this paper, we disentangle the conventional graph convolution operation into two independent operations: \\textit{Propagation} (\\textbf{P}) and \\textit{Transformation} (\\t"},"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":"2206.04361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T09:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"813166726ebb9c5db36c95c19fdcb03c003fd4cf3e7408f949ba6fed2300ae53","abstract_canon_sha256":"2bf8162b4dac5181d838df7ce0676663048e5b7c5216516710bb2fdbdc70e4c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:26.156296Z","signature_b64":"pEyPawo2c6/YmZWOaadIUY6gnlXVbpXsnaMsf5BXONfYAooRvBXWvXnlHq7YMAaFwy1x468oP3jEgAgM2C0IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b6b52e47c42010922965e0ac5b242991a4e6bcda7f96a8beea9949ddc822f8","last_reissued_at":"2026-07-05T04:30:26.155902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:26.155902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Degradation Hinders Deep Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Cui, Jun Gao, Wentao Zhang, Yikuan Xia, Yuezihan Jiang, Zeang Sheng, Zhi Yang, Ziqi Yin","submitted_at":"2022-06-09T09:02:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks.However, drastic performance degradation is always observed when a GNN is stacked with many layers. As a result, most GNNs only have shallow architectures, which limits their expressive power and exploitation of deep neighborhoods.Most recent studies attribute the performance degradation of deep GNNs to the \\textit{over-smoothing} issue. In this paper, we disentangle the conventional graph convolution operation into two independent operations: \\textit{Propagation} (\\textbf{P}) and \\textit{Transformation} (\\t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04361","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/2206.04361/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":"2206.04361","created_at":"2026-07-05T04:30:26.155961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04361v1","created_at":"2026-07-05T04:30:26.155961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04361","created_at":"2026-07-05T04:30:26.155961+00:00"},{"alias_kind":"pith_short_12","alias_value":"LC3LKLSHYQQB","created_at":"2026-07-05T04:30:26.155961+00:00"},{"alias_kind":"pith_short_16","alias_value":"LC3LKLSHYQQBBERJ","created_at":"2026-07-05T04:30:26.155961+00:00"},{"alias_kind":"pith_short_8","alias_value":"LC3LKLSH","created_at":"2026-07-05T04:30:26.155961+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/LC3LKLSHYQQBBERJMXQKYWZEFG","json":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG.json","graph_json":"https://pith.science/api/pith-number/LC3LKLSHYQQBBERJMXQKYWZEFG/graph.json","events_json":"https://pith.science/api/pith-number/LC3LKLSHYQQBBERJMXQKYWZEFG/events.json","paper":"https://pith.science/paper/LC3LKLSH"},"agent_actions":{"view_html":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG","download_json":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG.json","view_paper":"https://pith.science/paper/LC3LKLSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04361&json=true","fetch_graph":"https://pith.science/api/pith-number/LC3LKLSHYQQBBERJMXQKYWZEFG/graph.json","fetch_events":"https://pith.science/api/pith-number/LC3LKLSHYQQBBERJMXQKYWZEFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG/action/storage_attestation","attest_author":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG/action/author_attestation","sign_citation":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG/action/citation_signature","submit_replication":"https://pith.science/pith/LC3LKLSHYQQBBERJMXQKYWZEFG/action/replication_record"}},"created_at":"2026-07-05T04:30:26.155961+00:00","updated_at":"2026-07-05T04:30:26.155961+00:00"}