{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHAYDREXT42ZRBVM7VTVWGFS3M","short_pith_number":"pith:EHAYDREX","schema_version":"1.0","canonical_sha256":"21c181c4979f359886acfd675b18b2db212f5b5336cc6efdb9b07256da47e99b","source":{"kind":"arxiv","id":"2402.15326","version":2},"attestation_state":"computed","paper":{"title":"Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Congying Han, Tiande Guo, Tianshu Yu, Weichen Zhao, Xinyan Wang","submitted_at":"2024-02-23T13:44:57Z","abstract_excerpt":"This paper presents an analytical study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs). Generalizing beyond extant approaches grounded in random walk analysis or particle systems, we approach this problem through operator semigroup theory. This theoretical framework allows us to rigorously prove that oversmoothing is intrinsically linked to the ergodicity of the diffusion operator. Relying on semigroup method, we can quantitatively analyze the dynamic of graph diffusion and give a specific mathematical form of the smoothing feature by ergodicity and invariant measur"},"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":"2402.15326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T13:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"052306633e51d3e17cb5086866beba523178dc2b68afe2513c5a20161eaf051c","abstract_canon_sha256":"5cc25f12360df775661a8bac9abe815633d82d62e3323c3b8cbce668e010cfa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:24.384085Z","signature_b64":"WomRxieNY63AGbT4P72Wlah1PiAPJstTVs6iU+tsDI02CwlMcmN65xB3CZIGJxttbfC5QQOpt44HS8GY0JmbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21c181c4979f359886acfd675b18b2db212f5b5336cc6efdb9b07256da47e99b","last_reissued_at":"2026-07-05T10:37:24.383200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:24.383200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Congying Han, Tiande Guo, Tianshu Yu, Weichen Zhao, Xinyan Wang","submitted_at":"2024-02-23T13:44:57Z","abstract_excerpt":"This paper presents an analytical study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs). Generalizing beyond extant approaches grounded in random walk analysis or particle systems, we approach this problem through operator semigroup theory. This theoretical framework allows us to rigorously prove that oversmoothing is intrinsically linked to the ergodicity of the diffusion operator. Relying on semigroup method, we can quantitatively analyze the dynamic of graph diffusion and give a specific mathematical form of the smoothing feature by ergodicity and invariant measur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15326","kind":"arxiv","version":2},"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/2402.15326/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":"2402.15326","created_at":"2026-07-05T10:37:24.383307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15326v2","created_at":"2026-07-05T10:37:24.383307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15326","created_at":"2026-07-05T10:37:24.383307+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHAYDREXT42Z","created_at":"2026-07-05T10:37:24.383307+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHAYDREXT42ZRBVM","created_at":"2026-07-05T10:37:24.383307+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHAYDREX","created_at":"2026-07-05T10:37:24.383307+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/EHAYDREXT42ZRBVM7VTVWGFS3M","json":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M.json","graph_json":"https://pith.science/api/pith-number/EHAYDREXT42ZRBVM7VTVWGFS3M/graph.json","events_json":"https://pith.science/api/pith-number/EHAYDREXT42ZRBVM7VTVWGFS3M/events.json","paper":"https://pith.science/paper/EHAYDREX"},"agent_actions":{"view_html":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M","download_json":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M.json","view_paper":"https://pith.science/paper/EHAYDREX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15326&json=true","fetch_graph":"https://pith.science/api/pith-number/EHAYDREXT42ZRBVM7VTVWGFS3M/graph.json","fetch_events":"https://pith.science/api/pith-number/EHAYDREXT42ZRBVM7VTVWGFS3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M/action/storage_attestation","attest_author":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M/action/author_attestation","sign_citation":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M/action/citation_signature","submit_replication":"https://pith.science/pith/EHAYDREXT42ZRBVM7VTVWGFS3M/action/replication_record"}},"created_at":"2026-07-05T10:37:24.383307+00:00","updated_at":"2026-07-05T10:37:24.383307+00:00"}