{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2HH3YTASKVTMOCZH4F5WKL72TG","short_pith_number":"pith:2HH3YTAS","schema_version":"1.0","canonical_sha256":"d1cfbc4c125566c70b27e17b652ffa999651cdbec6bf4a4e00d939f960813d61","source":{"kind":"arxiv","id":"1911.05076","version":3},"attestation_state":"computed","paper":{"title":"Constant Curvature Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Gregor Bachmann, Octavian-Eugen Ganea","submitted_at":"2019-11-12T16:57:00Z","abstract_excerpt":"Interest has been rising lately towards methods representing data in non-Euclidean spaces, e.g. hyperbolic or spherical, that provide specific inductive biases useful for certain real-world data properties, e.g. scale-free, hierarchical or cyclical. However, the popular graph neural networks are currently limited in modeling data only via Euclidean geometry and associated vector space operations. Here, we bridge this gap by proposing mathematically grounded generalizations of graph convolutional networks (GCN) to (products of) constant curvature spaces. We do this by i) introducing a unified f"},"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":"1911.05076","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T16:57:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5486705c471c17c3e9f345ab8994c3c5ba2e02ad6c949cf14620fea71d520ceb","abstract_canon_sha256":"4fddaf6ce6787593d3d28724e006cb0a6f50017ec39b50cad0d7ed309053a074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:41.475784Z","signature_b64":"qv2ihFNpTNyrclCbatOgG27xPMolom12K4sgvsGILq8ZlnyfOjLVG2aG012fIvP9u9YL4W2FblkppZwsFDKEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1cfbc4c125566c70b27e17b652ffa999651cdbec6bf4a4e00d939f960813d61","last_reissued_at":"2026-07-05T01:03:41.475179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:41.475179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constant Curvature Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Gregor Bachmann, Octavian-Eugen Ganea","submitted_at":"2019-11-12T16:57:00Z","abstract_excerpt":"Interest has been rising lately towards methods representing data in non-Euclidean spaces, e.g. hyperbolic or spherical, that provide specific inductive biases useful for certain real-world data properties, e.g. scale-free, hierarchical or cyclical. However, the popular graph neural networks are currently limited in modeling data only via Euclidean geometry and associated vector space operations. Here, we bridge this gap by proposing mathematically grounded generalizations of graph convolutional networks (GCN) to (products of) constant curvature spaces. We do this by i) introducing a unified f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05076","kind":"arxiv","version":3},"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/1911.05076/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":"1911.05076","created_at":"2026-07-05T01:03:41.475235+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05076v3","created_at":"2026-07-05T01:03:41.475235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05076","created_at":"2026-07-05T01:03:41.475235+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HH3YTASKVTM","created_at":"2026-07-05T01:03:41.475235+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HH3YTASKVTMOCZH","created_at":"2026-07-05T01:03:41.475235+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HH3YTAS","created_at":"2026-07-05T01:03:41.475235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25600","citing_title":"Two-dimensional Hyperbolic RNN Neural Quantum State","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24337","citing_title":"New non-Euclidean neural quantum states from additional types of hyperbolic recurrent neural networks","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG","json":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG.json","graph_json":"https://pith.science/api/pith-number/2HH3YTASKVTMOCZH4F5WKL72TG/graph.json","events_json":"https://pith.science/api/pith-number/2HH3YTASKVTMOCZH4F5WKL72TG/events.json","paper":"https://pith.science/paper/2HH3YTAS"},"agent_actions":{"view_html":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG","download_json":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG.json","view_paper":"https://pith.science/paper/2HH3YTAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05076&json=true","fetch_graph":"https://pith.science/api/pith-number/2HH3YTASKVTMOCZH4F5WKL72TG/graph.json","fetch_events":"https://pith.science/api/pith-number/2HH3YTASKVTMOCZH4F5WKL72TG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG/action/storage_attestation","attest_author":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG/action/author_attestation","sign_citation":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG/action/citation_signature","submit_replication":"https://pith.science/pith/2HH3YTASKVTMOCZH4F5WKL72TG/action/replication_record"}},"created_at":"2026-07-05T01:03:41.475235+00:00","updated_at":"2026-07-05T01:03:41.475235+00:00"}