{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2QWGS4SKPLEF4EZZPXMZOAX3KN","short_pith_number":"pith:2QWGS4SK","schema_version":"1.0","canonical_sha256":"d42c69724a7ac85e13397dd99702fb5351cc1a682a5f0db334850335608d4a87","source":{"kind":"arxiv","id":"2605.21247","version":1},"attestation_state":"computed","paper":{"title":"Graph Navier Stokes Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guangsi Shi, Hongye Cheng, Shirui Pan, Tianyu Wang, Yu Gong, Yuxiao Li, Zexing Zhao","submitted_at":"2026-05-20T14:36:52Z","abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the oversmoothing problem, where node features become indistinguishable as the network depth increases. Inspired by the Navier Stokes equations, we introduce Graph Navier Stokes Networks (GNSN), a novel architecture that transcends conventional diffusion-based message passing by incorporating convection into graph structures. GNSN defines a dynamic velocity fie"},"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":"2605.21247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:36:52Z","cross_cats_sorted":[],"title_canon_sha256":"75891c965ee42ac91e7a85c26f18aa9a1c769479f3637ae9f105ae6ea49d255d","abstract_canon_sha256":"75701ade9a2687598726c55da157292114a8500d3077bf1332d99bd55fa6820a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:24.794718Z","signature_b64":"8ozYtT1AmKdc/BEgYst2CJdG5H6q3sH9PdCvAP4O5T5f5GAmMZnisERJZl9hM4GLbbOg2Ajj6JcYJdVJgLWUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42c69724a7ac85e13397dd99702fb5351cc1a682a5f0db334850335608d4a87","last_reissued_at":"2026-05-21T02:05:24.793728Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:24.793728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Navier Stokes Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guangsi Shi, Hongye Cheng, Shirui Pan, Tianyu Wang, Yu Gong, Yuxiao Li, Zexing Zhao","submitted_at":"2026-05-20T14:36:52Z","abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the oversmoothing problem, where node features become indistinguishable as the network depth increases. Inspired by the Navier Stokes equations, we introduce Graph Navier Stokes Networks (GNSN), a novel architecture that transcends conventional diffusion-based message passing by incorporating convection into graph structures. GNSN defines a dynamic velocity fie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21247","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/2605.21247/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":"2605.21247","created_at":"2026-05-21T02:05:24.793841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21247v1","created_at":"2026-05-21T02:05:24.793841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21247","created_at":"2026-05-21T02:05:24.793841+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QWGS4SKPLEF","created_at":"2026-05-21T02:05:24.793841+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QWGS4SKPLEF4EZZ","created_at":"2026-05-21T02:05:24.793841+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QWGS4SK","created_at":"2026-05-21T02:05:24.793841+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/2QWGS4SKPLEF4EZZPXMZOAX3KN","json":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN.json","graph_json":"https://pith.science/api/pith-number/2QWGS4SKPLEF4EZZPXMZOAX3KN/graph.json","events_json":"https://pith.science/api/pith-number/2QWGS4SKPLEF4EZZPXMZOAX3KN/events.json","paper":"https://pith.science/paper/2QWGS4SK"},"agent_actions":{"view_html":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN","download_json":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN.json","view_paper":"https://pith.science/paper/2QWGS4SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21247&json=true","fetch_graph":"https://pith.science/api/pith-number/2QWGS4SKPLEF4EZZPXMZOAX3KN/graph.json","fetch_events":"https://pith.science/api/pith-number/2QWGS4SKPLEF4EZZPXMZOAX3KN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN/action/storage_attestation","attest_author":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN/action/author_attestation","sign_citation":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN/action/citation_signature","submit_replication":"https://pith.science/pith/2QWGS4SKPLEF4EZZPXMZOAX3KN/action/replication_record"}},"created_at":"2026-05-21T02:05:24.793841+00:00","updated_at":"2026-05-21T02:05:24.793841+00:00"}