{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RXQVZE3GURGQR5NES5YWTPOKXM","short_pith_number":"pith:RXQVZE3G","schema_version":"1.0","canonical_sha256":"8de15c9366a44d08f5a4977169bdcabb3eae7ec6fc411958ba67273759b838a4","source":{"kind":"arxiv","id":"2105.14686","version":3},"attestation_state":"computed","paper":{"title":"Fully Hyperbolic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hexu Zhao, Jie Zhou, Maosong Sun, Peng Li, Weize Chen, Xu Han, Yankai Lin, Zhiyuan Liu","submitted_at":"2021-05-31T03:36:49Z","abstract_excerpt":"Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in a hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic space. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operation"},"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":"2105.14686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T03:36:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"daa0ea3aa234d129351758ab05e66281162d81966bd67a811f850ac4bdd6cfa8","abstract_canon_sha256":"df39d6a4ec848ac35d7d374340299ebaaf660e1794bd5504a5236935d3a2adc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:31.309598Z","signature_b64":"bPIKDL509LhXxzS824MATb+GCjp4F8h1wuYqKUQOUhXRuzXasyEISxnJyw8WuL55JyMJzlNROp2IvJ3T4K1mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de15c9366a44d08f5a4977169bdcabb3eae7ec6fc411958ba67273759b838a4","last_reissued_at":"2026-07-05T04:05:31.309071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:31.309071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Hyperbolic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hexu Zhao, Jie Zhou, Maosong Sun, Peng Li, Weize Chen, Xu Han, Yankai Lin, Zhiyuan Liu","submitted_at":"2021-05-31T03:36:49Z","abstract_excerpt":"Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in a hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic space. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14686","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/2105.14686/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":"2105.14686","created_at":"2026-07-05T04:05:31.309128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14686v3","created_at":"2026-07-05T04:05:31.309128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14686","created_at":"2026-07-05T04:05:31.309128+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXQVZE3GURGQ","created_at":"2026-07-05T04:05:31.309128+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXQVZE3GURGQR5NE","created_at":"2026-07-05T04:05:31.309128+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXQVZE3G","created_at":"2026-07-05T04:05:31.309128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25600","citing_title":"Two-dimensional Hyperbolic RNN Neural Quantum State","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24337","citing_title":"New non-Euclidean neural quantum states from hyperbolic Lorentz recurrent architectures","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20629","citing_title":"Rates of forgetting for the sequentially Markov coalescent","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM","json":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM.json","graph_json":"https://pith.science/api/pith-number/RXQVZE3GURGQR5NES5YWTPOKXM/graph.json","events_json":"https://pith.science/api/pith-number/RXQVZE3GURGQR5NES5YWTPOKXM/events.json","paper":"https://pith.science/paper/RXQVZE3G"},"agent_actions":{"view_html":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM","download_json":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM.json","view_paper":"https://pith.science/paper/RXQVZE3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14686&json=true","fetch_graph":"https://pith.science/api/pith-number/RXQVZE3GURGQR5NES5YWTPOKXM/graph.json","fetch_events":"https://pith.science/api/pith-number/RXQVZE3GURGQR5NES5YWTPOKXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM/action/storage_attestation","attest_author":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM/action/author_attestation","sign_citation":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM/action/citation_signature","submit_replication":"https://pith.science/pith/RXQVZE3GURGQR5NES5YWTPOKXM/action/replication_record"}},"created_at":"2026-07-05T04:05:31.309128+00:00","updated_at":"2026-07-05T04:05:31.309128+00:00"}