{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZNIAJWHK5TRDFHAQOYYYJLDVT","short_pith_number":"pith:WZNIAJWH","schema_version":"1.0","canonical_sha256":"b65a8026c757671194e083b18c2563acff30519df338e598443af60458add0d4","source":{"kind":"arxiv","id":"2412.04064","version":1},"attestation_state":"computed","paper":{"title":"Graph Neural Networks Need Cluster-Normalize-Activate Modules","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arseny Skryagin, Devendra Singh Dhami, Felix Divo, Kristian Kersting, Mohammad Amin Ali","submitted_at":"2024-12-05T10:59:20Z","abstract_excerpt":"Graph Neural Networks (GNNs) are non-Euclidean deep learning models for graph-structured data. Despite their successful and diverse applications, oversmoothing prohibits deep architectures due to node features converging to a single fixed point. This severely limits their potential to solve complex tasks. To counteract this tendency, we propose a plug-and-play module consisting of three steps: Cluster-Normalize-Activate (CNA). By applying CNA modules, GNNs search and form super nodes in each layer, which are normalized and activated individually. We demonstrate in node classification and prope"},"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":"2412.04064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T10:59:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"780b1c1ca9f4339af6212bb07b94142f9d495ceb75ada30c239b70024b534f24","abstract_canon_sha256":"fbdadbb98d7872dfb726cf4edd23459905b0d4caf00fc6b5b190a8f57d728dc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:58.608830Z","signature_b64":"FFzrCC+CXz/d41Icy4anBGPxj5khxLlXyr81lAeRpEdasOdOYowVnt1oSdS1VyQRW3cOCOiEJBRLnWAYeQssAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b65a8026c757671194e083b18c2563acff30519df338e598443af60458add0d4","last_reissued_at":"2026-07-05T09:44:58.608411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:58.608411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Neural Networks Need Cluster-Normalize-Activate Modules","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arseny Skryagin, Devendra Singh Dhami, Felix Divo, Kristian Kersting, Mohammad Amin Ali","submitted_at":"2024-12-05T10:59:20Z","abstract_excerpt":"Graph Neural Networks (GNNs) are non-Euclidean deep learning models for graph-structured data. Despite their successful and diverse applications, oversmoothing prohibits deep architectures due to node features converging to a single fixed point. This severely limits their potential to solve complex tasks. To counteract this tendency, we propose a plug-and-play module consisting of three steps: Cluster-Normalize-Activate (CNA). By applying CNA modules, GNNs search and form super nodes in each layer, which are normalized and activated individually. We demonstrate in node classification and prope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04064","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/2412.04064/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":"2412.04064","created_at":"2026-07-05T09:44:58.608470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04064v1","created_at":"2026-07-05T09:44:58.608470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04064","created_at":"2026-07-05T09:44:58.608470+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZNIAJWHK5TR","created_at":"2026-07-05T09:44:58.608470+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZNIAJWHK5TRDFHA","created_at":"2026-07-05T09:44:58.608470+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZNIAJWH","created_at":"2026-07-05T09:44:58.608470+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/WZNIAJWHK5TRDFHAQOYYYJLDVT","json":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT.json","graph_json":"https://pith.science/api/pith-number/WZNIAJWHK5TRDFHAQOYYYJLDVT/graph.json","events_json":"https://pith.science/api/pith-number/WZNIAJWHK5TRDFHAQOYYYJLDVT/events.json","paper":"https://pith.science/paper/WZNIAJWH"},"agent_actions":{"view_html":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT","download_json":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT.json","view_paper":"https://pith.science/paper/WZNIAJWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04064&json=true","fetch_graph":"https://pith.science/api/pith-number/WZNIAJWHK5TRDFHAQOYYYJLDVT/graph.json","fetch_events":"https://pith.science/api/pith-number/WZNIAJWHK5TRDFHAQOYYYJLDVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT/action/storage_attestation","attest_author":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT/action/author_attestation","sign_citation":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT/action/citation_signature","submit_replication":"https://pith.science/pith/WZNIAJWHK5TRDFHAQOYYYJLDVT/action/replication_record"}},"created_at":"2026-07-05T09:44:58.608470+00:00","updated_at":"2026-07-05T09:44:58.608470+00:00"}