{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WXPIQMJSOW5ORU74ZLOWOU4I65","short_pith_number":"pith:WXPIQMJS","schema_version":"1.0","canonical_sha256":"b5de88313275bae8d3fccadd675388f7594b7a8c9af73ffb9c1f16c7c7376eb2","source":{"kind":"arxiv","id":"2505.23014","version":1},"attestation_state":"computed","paper":{"title":"Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haikuo Li, Jiawei Sheng, Juwei Yue, Li Guo, Taoyu Su, Tingwen Liu, Xiaodong Li","submitted_at":"2025-05-29T02:49:26Z","abstract_excerpt":"Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensure topological features. In this paper, we formulates message passing as a system of hyperbolic partial differential equations (hyperbolic PDEs), constituting a dynamical system that explicitly maps node representations into a particular solution space. This solution space is spanned by a set of eigenvectors describing the topological structure of graphs. Within this system, fo"},"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":"2505.23014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T02:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"ed0940d7f75238f5d8256576775aa925799b80d9a2d6ead8655f58084aae224d","abstract_canon_sha256":"277c738caf0c94366691c58c06c7e1b5f3eccbbce5211f30173bdabcc565dd69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.587253Z","signature_b64":"EiAovCt1Kz/Oxq5IVrRFZyYP5T3FmwEMPgA9Mofq65BPFMoH5SXYm+nVjQltgFird6pFnBCOPkv5Z4cvkhVUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5de88313275bae8d3fccadd675388f7594b7a8c9af73ffb9c1f16c7c7376eb2","last_reissued_at":"2026-07-05T11:11:53.586765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.586765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haikuo Li, Jiawei Sheng, Juwei Yue, Li Guo, Taoyu Su, Tingwen Liu, Xiaodong Li","submitted_at":"2025-05-29T02:49:26Z","abstract_excerpt":"Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensure topological features. In this paper, we formulates message passing as a system of hyperbolic partial differential equations (hyperbolic PDEs), constituting a dynamical system that explicitly maps node representations into a particular solution space. This solution space is spanned by a set of eigenvectors describing the topological structure of graphs. Within this system, fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23014","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/2505.23014/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":"2505.23014","created_at":"2026-07-05T11:11:53.586823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23014v1","created_at":"2026-07-05T11:11:53.586823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23014","created_at":"2026-07-05T11:11:53.586823+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXPIQMJSOW5O","created_at":"2026-07-05T11:11:53.586823+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXPIQMJSOW5ORU74","created_at":"2026-07-05T11:11:53.586823+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXPIQMJS","created_at":"2026-07-05T11:11:53.586823+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/WXPIQMJSOW5ORU74ZLOWOU4I65","json":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65.json","graph_json":"https://pith.science/api/pith-number/WXPIQMJSOW5ORU74ZLOWOU4I65/graph.json","events_json":"https://pith.science/api/pith-number/WXPIQMJSOW5ORU74ZLOWOU4I65/events.json","paper":"https://pith.science/paper/WXPIQMJS"},"agent_actions":{"view_html":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65","download_json":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65.json","view_paper":"https://pith.science/paper/WXPIQMJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23014&json=true","fetch_graph":"https://pith.science/api/pith-number/WXPIQMJSOW5ORU74ZLOWOU4I65/graph.json","fetch_events":"https://pith.science/api/pith-number/WXPIQMJSOW5ORU74ZLOWOU4I65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65/action/storage_attestation","attest_author":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65/action/author_attestation","sign_citation":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65/action/citation_signature","submit_replication":"https://pith.science/pith/WXPIQMJSOW5ORU74ZLOWOU4I65/action/replication_record"}},"created_at":"2026-07-05T11:11:53.586823+00:00","updated_at":"2026-07-05T11:11:53.586823+00:00"}