{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FM2KN366E5C2HPZVPM6GAKIJY7","short_pith_number":"pith:FM2KN366","schema_version":"1.0","canonical_sha256":"2b34a6efde2745a3bf357b3c602909c7c5ecd591b1c33dcc336c696e49a25786","source":{"kind":"arxiv","id":"2006.08210","version":3},"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":"Ryohei Shimizu, Tatsuya Harada, Yusuke Mukuta","submitted_at":"2020-06-15T08:23:20Z","abstract_excerpt":"Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this study, we generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar\\'e ball model. This novel methodology constructs a multinomial logistic regression, fully-connected layers, convolutional layers, and attention mechanisms under a unified mathematical interpretation, without increasing the parameters. Expe"},"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":"2006.08210","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T08:23:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3a92510ec011c22198615de4b04787b0dba18a95e1e325ccc0f3398dcff384ac","abstract_canon_sha256":"cc993dd49e987849e0b924916e65149d6ddc075549d5d3015c86804c0e3ff4be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:57.351581Z","signature_b64":"x2/X02wf2FAU/GtWFCTBvagmCZ2W9PH2KzLhtXqFZ8S+EH0swm2j2+x+rjsE++vLQJXH1I/VM8IWPqMhnhFoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b34a6efde2745a3bf357b3c602909c7c5ecd591b1c33dcc336c696e49a25786","last_reissued_at":"2026-07-05T02:23:57.351089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:57.351089Z","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":"Ryohei Shimizu, Tatsuya Harada, Yusuke Mukuta","submitted_at":"2020-06-15T08:23:20Z","abstract_excerpt":"Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this study, we generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar\\'e ball model. This novel methodology constructs a multinomial logistic regression, fully-connected layers, convolutional layers, and attention mechanisms under a unified mathematical interpretation, without increasing the parameters. Expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08210","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/2006.08210/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":"2006.08210","created_at":"2026-07-05T02:23:57.351148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08210v3","created_at":"2026-07-05T02:23:57.351148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08210","created_at":"2026-07-05T02:23:57.351148+00:00"},{"alias_kind":"pith_short_12","alias_value":"FM2KN366E5C2","created_at":"2026-07-05T02:23:57.351148+00:00"},{"alias_kind":"pith_short_16","alias_value":"FM2KN366E5C2HPZV","created_at":"2026-07-05T02:23:57.351148+00:00"},{"alias_kind":"pith_short_8","alias_value":"FM2KN366","created_at":"2026-07-05T02:23:57.351148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25600","citing_title":"Two-dimensional Hyperbolic RNN Neural Quantum State","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00556","citing_title":"Group-Equivariant Poincar\\'e Convolutional Networks","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29057","citing_title":"LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24337","citing_title":"New non-Euclidean neural quantum states from hyperbolic Lorentz recurrent architectures","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00467","citing_title":"Batch Normalization for Neural Networks on Complex Domains","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7","json":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7.json","graph_json":"https://pith.science/api/pith-number/FM2KN366E5C2HPZVPM6GAKIJY7/graph.json","events_json":"https://pith.science/api/pith-number/FM2KN366E5C2HPZVPM6GAKIJY7/events.json","paper":"https://pith.science/paper/FM2KN366"},"agent_actions":{"view_html":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7","download_json":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7.json","view_paper":"https://pith.science/paper/FM2KN366","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08210&json=true","fetch_graph":"https://pith.science/api/pith-number/FM2KN366E5C2HPZVPM6GAKIJY7/graph.json","fetch_events":"https://pith.science/api/pith-number/FM2KN366E5C2HPZVPM6GAKIJY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7/action/storage_attestation","attest_author":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7/action/author_attestation","sign_citation":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7/action/citation_signature","submit_replication":"https://pith.science/pith/FM2KN366E5C2HPZVPM6GAKIJY7/action/replication_record"}},"created_at":"2026-07-05T02:23:57.351148+00:00","updated_at":"2026-07-05T02:23:57.351148+00:00"}