{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UT3CREEFGMCFCOXR4CLGVLND3L","short_pith_number":"pith:UT3CREEF","schema_version":"1.0","canonical_sha256":"a4f62890853304513af1e0966aada3daf0b9ef50c60b190975af80400d2b8cab","source":{"kind":"arxiv","id":"2311.03260","version":2},"attestation_state":"computed","paper":{"title":"From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotada Honda, Shugo Nakamura, Takashi Sano, Tan M. Nguyen, Tuan Nguyen, Vinh Nguyen","submitted_at":"2023-11-06T16:47:17Z","abstract_excerpt":"We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases. The Kuramoto model captures the synchronization behavior of non-linear coupled oscillators. Under the view of coupled oscillators, we first show the connection between Kuramoto model and basic GNN and then over-smoothing phenomenon in GNNs can be interpreted as phase synchronization in Kuramoto model. The Kura"},"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":"2311.03260","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T16:47:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a706017fcaf0b3715efb0a0b78eab83000d797bb1a7e0a8cff4de93f2db9a4f2","abstract_canon_sha256":"f6b22e1544f684073a073da8d16bfd00cc1956142e3bbf06879a7c9390fd94ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:42.662458Z","signature_b64":"64GHzLiA+dR+rqGo9cVW0VmIw5yWo987xNqrNzd5HM4Z/kigMHxNs70IhEXMle1ow4D/PwLNYPaXQmi1FVv7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4f62890853304513af1e0966aada3daf0b9ef50c60b190975af80400d2b8cab","last_reissued_at":"2026-07-05T07:52:42.661924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:42.661924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotada Honda, Shugo Nakamura, Takashi Sano, Tan M. Nguyen, Tuan Nguyen, Vinh Nguyen","submitted_at":"2023-11-06T16:47:17Z","abstract_excerpt":"We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases. The Kuramoto model captures the synchronization behavior of non-linear coupled oscillators. Under the view of coupled oscillators, we first show the connection between Kuramoto model and basic GNN and then over-smoothing phenomenon in GNNs can be interpreted as phase synchronization in Kuramoto model. The Kura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03260","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/2311.03260/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":"2311.03260","created_at":"2026-07-05T07:52:42.661989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03260v2","created_at":"2026-07-05T07:52:42.661989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03260","created_at":"2026-07-05T07:52:42.661989+00:00"},{"alias_kind":"pith_short_12","alias_value":"UT3CREEFGMCF","created_at":"2026-07-05T07:52:42.661989+00:00"},{"alias_kind":"pith_short_16","alias_value":"UT3CREEFGMCFCOXR","created_at":"2026-07-05T07:52:42.661989+00:00"},{"alias_kind":"pith_short_8","alias_value":"UT3CREEF","created_at":"2026-07-05T07:52:42.661989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24958","citing_title":"Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20441","citing_title":"Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L","json":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L.json","graph_json":"https://pith.science/api/pith-number/UT3CREEFGMCFCOXR4CLGVLND3L/graph.json","events_json":"https://pith.science/api/pith-number/UT3CREEFGMCFCOXR4CLGVLND3L/events.json","paper":"https://pith.science/paper/UT3CREEF"},"agent_actions":{"view_html":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L","download_json":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L.json","view_paper":"https://pith.science/paper/UT3CREEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03260&json=true","fetch_graph":"https://pith.science/api/pith-number/UT3CREEFGMCFCOXR4CLGVLND3L/graph.json","fetch_events":"https://pith.science/api/pith-number/UT3CREEFGMCFCOXR4CLGVLND3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L/action/storage_attestation","attest_author":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L/action/author_attestation","sign_citation":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L/action/citation_signature","submit_replication":"https://pith.science/pith/UT3CREEFGMCFCOXR4CLGVLND3L/action/replication_record"}},"created_at":"2026-07-05T07:52:42.661989+00:00","updated_at":"2026-07-05T07:52:42.661989+00:00"}