{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BFGC3K4JCYJGZNAVOOU3YIHYCG","short_pith_number":"pith:BFGC3K4J","schema_version":"1.0","canonical_sha256":"094c2dab8916126cb41573a9bc20f81184a3e090d4f23f27d8a850f8ef9148f9","source":{"kind":"arxiv","id":"2303.10993","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Oversmoothing in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael M. Bronstein, Siddhartha Mishra, T. Konstantin Rusch","submitted_at":"2023-03-20T10:21:29Z","abstract_excerpt":"Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we axiomatically define as the exponential convergence of suitable similarity measures on the node features. Our definition unifies previous approaches and gives rise to new quantitative measures of over-smoothing. Moreover, we empirically demonstrate this behavior for several over-smoothing measures on different graphs (small-, medium-, and large-scale). We also review several approaches for mitigating over-smoothing and empirically te"},"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":"2303.10993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T10:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"89800991a35ec05d2e9c55ab72119765bcb94f858ea21d5118a5b52c9b0ea21f","abstract_canon_sha256":"ffb5726c4a52c888f700d9b0b429ce91ee59764b426af7c1b41a9ec481829368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:38.916501Z","signature_b64":"Urx9ky8S3KvwCUQw0r4Q/h5ljL2kwZpGUhG4LvKTDrXKS+lONN6KcQEyg1DthNpdvMNMspJM/R/bGS1tjCrHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"094c2dab8916126cb41573a9bc20f81184a3e090d4f23f27d8a850f8ef9148f9","last_reissued_at":"2026-07-05T05:52:38.916099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:38.916099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Oversmoothing in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael M. Bronstein, Siddhartha Mishra, T. Konstantin Rusch","submitted_at":"2023-03-20T10:21:29Z","abstract_excerpt":"Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we axiomatically define as the exponential convergence of suitable similarity measures on the node features. Our definition unifies previous approaches and gives rise to new quantitative measures of over-smoothing. Moreover, we empirically demonstrate this behavior for several over-smoothing measures on different graphs (small-, medium-, and large-scale). We also review several approaches for mitigating over-smoothing and empirically te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10993","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/2303.10993/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":"2303.10993","created_at":"2026-07-05T05:52:38.916156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10993v1","created_at":"2026-07-05T05:52:38.916156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10993","created_at":"2026-07-05T05:52:38.916156+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFGC3K4JCYJG","created_at":"2026-07-05T05:52:38.916156+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFGC3K4JCYJGZNAV","created_at":"2026-07-05T05:52:38.916156+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFGC3K4J","created_at":"2026-07-05T05:52:38.916156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":34,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23572","citing_title":"A Spectral Theory of Normalized Corrected GNN Propagation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22167","citing_title":"Early-Exit Graph Neural Networks for Link Prediction","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21333","citing_title":"Ramanujan Graph Rewiring with Non Negative Resistance Curvature","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20283","citing_title":"Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement","ref_index":36,"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":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10071","citing_title":"Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23239","citing_title":"Self-supervised Adversarial Purification for Graph Neural Networks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31414","citing_title":"Beyond Instance-Level Alignment and Uniformity: Semantic Factor Learning for Collaborative Filtering","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03068","citing_title":"Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Graphs","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23251","citing_title":"Attention mechanism for scalable mesh-based neural surrogates of free-surface fluids","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23467","citing_title":"S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23239","citing_title":"Self-supervised Adversarial Purification for Graph Neural Networks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2407.20067","citing_title":"xAI-Drop: Don't Use What You Cannot Explain","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2411.17429","citing_title":"Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08835","citing_title":"Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2501.15461","citing_title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22593","citing_title":"Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":18,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19324","citing_title":"BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20032","citing_title":"CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15524","citing_title":"Neural Point-Forms","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11541","citing_title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05456","citing_title":"Parameter-Efficient Conditioning for Material Generalization in Graph-Based Simulators","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14464","citing_title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG","json":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG.json","graph_json":"https://pith.science/api/pith-number/BFGC3K4JCYJGZNAVOOU3YIHYCG/graph.json","events_json":"https://pith.science/api/pith-number/BFGC3K4JCYJGZNAVOOU3YIHYCG/events.json","paper":"https://pith.science/paper/BFGC3K4J"},"agent_actions":{"view_html":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG","download_json":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG.json","view_paper":"https://pith.science/paper/BFGC3K4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10993&json=true","fetch_graph":"https://pith.science/api/pith-number/BFGC3K4JCYJGZNAVOOU3YIHYCG/graph.json","fetch_events":"https://pith.science/api/pith-number/BFGC3K4JCYJGZNAVOOU3YIHYCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG/action/storage_attestation","attest_author":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG/action/author_attestation","sign_citation":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG/action/citation_signature","submit_replication":"https://pith.science/pith/BFGC3K4JCYJGZNAVOOU3YIHYCG/action/replication_record"}},"created_at":"2026-07-05T05:52:38.916156+00:00","updated_at":"2026-07-05T05:52:38.916156+00:00"}