{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3JQEHRZMZ7KZGM2LS7DHICZZRZ","short_pith_number":"pith:3JQEHRZM","schema_version":"1.0","canonical_sha256":"da6043c72ccfd593334b97c6740b398e4b0ead4d8c39332f3e06e433d333ee4f","source":{"kind":"arxiv","id":"1805.09112","version":2},"attestation_state":"computed","paper":{"title":"Hyperbolic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea, Thomas Hofmann","submitted_at":"2018-05-23T13:08:07Z","abstract_excerpt":"Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network layers. This makes it hard to use hyperbolic embeddings in downstream tasks. Here, we bridge this gap in a principled manner by combining the formalism of M\\\"obius gyrovector spaces with the Riemannian geometry of the Poincar\\'e model of hyperbolic spaces. As a result, we derive hyp"},"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":"1805.09112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T13:08:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a821253ec28ceac4c21386f64cd488be7c30ede7ad327d779861396488cfd47","abstract_canon_sha256":"25488c9a0080505094003cd6bf24f44fd8083221ff423d5fed35eb449d798724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:08.625731Z","signature_b64":"rAmUzrByk8YeQhCBSaBxzF7yp94O/m6wHeTLhA8RaDMsShYOAKpBQZeLtgTgALhYHMXEcWwubhGaBvAZRKNHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da6043c72ccfd593334b97c6740b398e4b0ead4d8c39332f3e06e433d333ee4f","last_reissued_at":"2026-05-18T00:12:08.624988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:08.624988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea, Thomas Hofmann","submitted_at":"2018-05-23T13:08:07Z","abstract_excerpt":"Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network layers. This makes it hard to use hyperbolic embeddings in downstream tasks. Here, we bridge this gap in a principled manner by combining the formalism of M\\\"obius gyrovector spaces with the Riemannian geometry of the Poincar\\'e model of hyperbolic spaces. As a result, we derive hyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09112","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":""},"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":"1805.09112","created_at":"2026-05-18T00:12:08.625114+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09112v2","created_at":"2026-05-18T00:12:08.625114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09112","created_at":"2026-05-18T00:12:08.625114+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JQEHRZMZ7KZ","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JQEHRZMZ7KZGM2L","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JQEHRZM","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.08965","citing_title":"Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24337","citing_title":"New non-Euclidean neural quantum states from additional types of hyperbolic recurrent neural networks","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ","json":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ.json","graph_json":"https://pith.science/api/pith-number/3JQEHRZMZ7KZGM2LS7DHICZZRZ/graph.json","events_json":"https://pith.science/api/pith-number/3JQEHRZMZ7KZGM2LS7DHICZZRZ/events.json","paper":"https://pith.science/paper/3JQEHRZM"},"agent_actions":{"view_html":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ","download_json":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ.json","view_paper":"https://pith.science/paper/3JQEHRZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09112&json=true","fetch_graph":"https://pith.science/api/pith-number/3JQEHRZMZ7KZGM2LS7DHICZZRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3JQEHRZMZ7KZGM2LS7DHICZZRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ/action/storage_attestation","attest_author":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ/action/author_attestation","sign_citation":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ/action/citation_signature","submit_replication":"https://pith.science/pith/3JQEHRZMZ7KZGM2LS7DHICZZRZ/action/replication_record"}},"created_at":"2026-05-18T00:12:08.625114+00:00","updated_at":"2026-05-18T00:12:08.625114+00:00"}