{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MRV7KWVJLFEPFQHD6PWA33GAAP","short_pith_number":"pith:MRV7KWVJ","schema_version":"1.0","canonical_sha256":"646bf55aa95948f2c0e3f3ec0decc003e8c9884749d39df9df966fed497707c6","source":{"kind":"arxiv","id":"2006.13318","version":1},"attestation_state":"computed","paper":{"title":"A Note on Over-Smoothing for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Cai, Yusu Wang","submitted_at":"2020-06-23T20:36:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as over-smoothing, has been analyzed mostly in linear cases. In this paper, we build upon previous results \\cite{oono2019graph} to further analyze the over-smoothing effect in the general graph neural network architecture. We show when the weight matrix satisfies the conditions determined by the spectrum of augmented normalized Laplacian, the Dirichlet energy of embeddin"},"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":"2006.13318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T20:36:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6c7cafa4135a2e5667ab6065cdc847b977fc490d0426d40e24598a21776e49c7","abstract_canon_sha256":"728bdf83d8a5e0b231011bfd92d44e39e6d56c12ebe7ddf2c82db6de9aa4f2ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:14.507967Z","signature_b64":"00kWTbSfdzKvG4I0fhB+ykGlfSuvK7LiP5R6zmZuVOfjl93JIyF1DiL+zmMfcDBkc6M5dH1efCAGzEyXo8FZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"646bf55aa95948f2c0e3f3ec0decc003e8c9884749d39df9df966fed497707c6","last_reissued_at":"2026-07-05T01:13:14.507380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:14.507380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on Over-Smoothing for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Cai, Yusu Wang","submitted_at":"2020-06-23T20:36:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as over-smoothing, has been analyzed mostly in linear cases. In this paper, we build upon previous results \\cite{oono2019graph} to further analyze the over-smoothing effect in the general graph neural network architecture. We show when the weight matrix satisfies the conditions determined by the spectrum of augmented normalized Laplacian, the Dirichlet energy of embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13318","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/2006.13318/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":"2006.13318","created_at":"2026-07-05T01:13:14.507459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13318v1","created_at":"2026-07-05T01:13:14.507459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13318","created_at":"2026-07-05T01:13:14.507459+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRV7KWVJLFEP","created_at":"2026-07-05T01:13:14.507459+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRV7KWVJLFEPFQHD","created_at":"2026-07-05T01:13:14.507459+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRV7KWVJ","created_at":"2026-07-05T01:13:14.507459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19185","citing_title":"AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2409.08036","citing_title":"Heterogeneous Sheaf Neural Networks","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18387","citing_title":"Graph Hierarchical Recurrence for Long-Range Generalization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15524","citing_title":"Neural Point-Forms","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06443","citing_title":"How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05352","citing_title":"Smoothness Errors in Dynamics Models and How to Avoid Them","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03861","citing_title":"Aspect-Aware Content-Based Recommendations for Mathematical Research Papers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23324","citing_title":"Layer Embedding Deep Fusion Graph Neural Network","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19028","citing_title":"Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11791","citing_title":"A Mechanistic Analysis of Looped Reasoning Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP","json":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP.json","graph_json":"https://pith.science/api/pith-number/MRV7KWVJLFEPFQHD6PWA33GAAP/graph.json","events_json":"https://pith.science/api/pith-number/MRV7KWVJLFEPFQHD6PWA33GAAP/events.json","paper":"https://pith.science/paper/MRV7KWVJ"},"agent_actions":{"view_html":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP","download_json":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP.json","view_paper":"https://pith.science/paper/MRV7KWVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13318&json=true","fetch_graph":"https://pith.science/api/pith-number/MRV7KWVJLFEPFQHD6PWA33GAAP/graph.json","fetch_events":"https://pith.science/api/pith-number/MRV7KWVJLFEPFQHD6PWA33GAAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP/action/storage_attestation","attest_author":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP/action/author_attestation","sign_citation":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP/action/citation_signature","submit_replication":"https://pith.science/pith/MRV7KWVJLFEPFQHD6PWA33GAAP/action/replication_record"}},"created_at":"2026-07-05T01:13:14.507459+00:00","updated_at":"2026-07-05T01:13:14.507459+00:00"}