{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NG4QW2NTLVVA3VZPQ6APTKVA6P","short_pith_number":"pith:NG4QW2NT","schema_version":"1.0","canonical_sha256":"69b90b69b35d6a0dd72f8780f9aaa0f3e9f3c6a5737f420443c0c8f8114ba4fe","source":{"kind":"arxiv","id":"1902.02992","version":2},"attestation_state":"computed","paper":{"title":"A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masanori Koyama, Shoichiro Yamaguchi, Yasuhiro Fujita, Yoshihiro Nagano","submitted_at":"2019-02-08T09:42:06Z","abstract_excerpt":"Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure. In this paper, we present a novel hyperbolic distribution called \\textit{pseudo-hyperbolic Gaussian}, a Gaussian-like distribution on hyperbolic space whose density can be evaluated analytically and differentiated with respect to the parameters. Our distribution enables the gradient-based learning of the probabilistic models on hyperbolic space that could never have been considered before. Also, we can sample from this hyperbolic probability distribution"},"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":"1902.02992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-08T09:42:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f55c3eba1c37db47ad7d24ed75fa43e1f0544ba5ddd46146e1180026556a96e","abstract_canon_sha256":"25114c499cb63c240543064170c72e336d8f52570e487abf6bf7e6b2750ecb11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:35.860563Z","signature_b64":"YZnp2w8WYrhL1BvNjk3PdrcCmUkLTqHUrq9r50S8/GopvyG1IbgKJoU6cDe1a5xtMtYfMu20hyT2V5Qbb/KxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b90b69b35d6a0dd72f8780f9aaa0f3e9f3c6a5737f420443c0c8f8114ba4fe","last_reissued_at":"2026-05-17T23:46:35.859937Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:35.859937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masanori Koyama, Shoichiro Yamaguchi, Yasuhiro Fujita, Yoshihiro Nagano","submitted_at":"2019-02-08T09:42:06Z","abstract_excerpt":"Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure. In this paper, we present a novel hyperbolic distribution called \\textit{pseudo-hyperbolic Gaussian}, a Gaussian-like distribution on hyperbolic space whose density can be evaluated analytically and differentiated with respect to the parameters. Our distribution enables the gradient-based learning of the probabilistic models on hyperbolic space that could never have been considered before. Also, we can sample from this hyperbolic probability distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02992","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":"1902.02992","created_at":"2026-05-17T23:46:35.860037+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02992v2","created_at":"2026-05-17T23:46:35.860037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02992","created_at":"2026-05-17T23:46:35.860037+00:00"},{"alias_kind":"pith_short_12","alias_value":"NG4QW2NTLVVA","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NG4QW2NTLVVA3VZP","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NG4QW2NT","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P","json":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P.json","graph_json":"https://pith.science/api/pith-number/NG4QW2NTLVVA3VZPQ6APTKVA6P/graph.json","events_json":"https://pith.science/api/pith-number/NG4QW2NTLVVA3VZPQ6APTKVA6P/events.json","paper":"https://pith.science/paper/NG4QW2NT"},"agent_actions":{"view_html":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P","download_json":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P.json","view_paper":"https://pith.science/paper/NG4QW2NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02992&json=true","fetch_graph":"https://pith.science/api/pith-number/NG4QW2NTLVVA3VZPQ6APTKVA6P/graph.json","fetch_events":"https://pith.science/api/pith-number/NG4QW2NTLVVA3VZPQ6APTKVA6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P/action/storage_attestation","attest_author":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P/action/author_attestation","sign_citation":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P/action/citation_signature","submit_replication":"https://pith.science/pith/NG4QW2NTLVVA3VZPQ6APTKVA6P/action/replication_record"}},"created_at":"2026-05-17T23:46:35.860037+00:00","updated_at":"2026-05-17T23:46:35.860037+00:00"}