{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E6TJG3LQUFZDSKU7MHNJLPBO5X","short_pith_number":"pith:E6TJG3LQ","schema_version":"1.0","canonical_sha256":"27a6936d70a172392a9f61da95bc2eedd518b6eca6060c7f2e78181dd74a6e70","source":{"kind":"arxiv","id":"2505.24353","version":1},"attestation_state":"computed","paper":{"title":"Cartan Networks: Group theoretical Hyperbolic Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Federico Milanesio, Guido Sanguinetti, Matteo Santoro, Pietro G. Fr\\'e","submitted_at":"2025-05-30T08:45:53Z","abstract_excerpt":"Hyperbolic deep learning leverages the metric properties of hyperbolic spaces to develop efficient and informative embeddings of hierarchical data. Here, we focus on the solvable group structure of hyperbolic spaces, which follows naturally from their construction as symmetric spaces. This dual nature of Lie group and Riemannian manifold allows us to propose a new class of hyperbolic deep learning algorithms where group homomorphisms are interleaved with metric-preserving diffeomorphisms. The resulting algorithms, which we call Cartan networks, show promising results on various benchmark data "},"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":"2505.24353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T08:45:53Z","cross_cats_sorted":[],"title_canon_sha256":"f2fb87de121edbc04f36c5753f7e5aa296fd60b9bedacaf94ae9453515b65ecc","abstract_canon_sha256":"8a700a2c459443be09103ed19550c1d681663208481742759d47b7fbd4082c42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:47.416402Z","signature_b64":"BeC7KQ9A6AREqyBPbu3fC/Hyyt0G2ojStiaQQmuNzImvpa+dc8vpr+mmfMGPqf9dwFcy9mYo5u+JpheF6SjWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27a6936d70a172392a9f61da95bc2eedd518b6eca6060c7f2e78181dd74a6e70","last_reissued_at":"2026-07-05T11:12:47.415838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:47.415838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cartan Networks: Group theoretical Hyperbolic Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Federico Milanesio, Guido Sanguinetti, Matteo Santoro, Pietro G. Fr\\'e","submitted_at":"2025-05-30T08:45:53Z","abstract_excerpt":"Hyperbolic deep learning leverages the metric properties of hyperbolic spaces to develop efficient and informative embeddings of hierarchical data. Here, we focus on the solvable group structure of hyperbolic spaces, which follows naturally from their construction as symmetric spaces. This dual nature of Lie group and Riemannian manifold allows us to propose a new class of hyperbolic deep learning algorithms where group homomorphisms are interleaved with metric-preserving diffeomorphisms. The resulting algorithms, which we call Cartan networks, show promising results on various benchmark data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24353","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/2505.24353/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":"2505.24353","created_at":"2026-07-05T11:12:47.415897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24353v1","created_at":"2026-07-05T11:12:47.415897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24353","created_at":"2026-07-05T11:12:47.415897+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6TJG3LQUFZD","created_at":"2026-07-05T11:12:47.415897+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6TJG3LQUFZDSKU7","created_at":"2026-07-05T11:12:47.415897+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6TJG3LQ","created_at":"2026-07-05T11:12:47.415897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09438","citing_title":"The macroscopic Kaehler metric of Geometric Thermodynamics versus the microscopic one on the Event Manifold: Exact Partition Functions on CV manifolds. Extended Souriau temperatures and spontaneous ma","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X","json":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X.json","graph_json":"https://pith.science/api/pith-number/E6TJG3LQUFZDSKU7MHNJLPBO5X/graph.json","events_json":"https://pith.science/api/pith-number/E6TJG3LQUFZDSKU7MHNJLPBO5X/events.json","paper":"https://pith.science/paper/E6TJG3LQ"},"agent_actions":{"view_html":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X","download_json":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X.json","view_paper":"https://pith.science/paper/E6TJG3LQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24353&json=true","fetch_graph":"https://pith.science/api/pith-number/E6TJG3LQUFZDSKU7MHNJLPBO5X/graph.json","fetch_events":"https://pith.science/api/pith-number/E6TJG3LQUFZDSKU7MHNJLPBO5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X/action/storage_attestation","attest_author":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X/action/author_attestation","sign_citation":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X/action/citation_signature","submit_replication":"https://pith.science/pith/E6TJG3LQUFZDSKU7MHNJLPBO5X/action/replication_record"}},"created_at":"2026-07-05T11:12:47.415897+00:00","updated_at":"2026-07-05T11:12:47.415897+00:00"}