{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KR562SSW4GP6BDIDIV7WQU7X7T","short_pith_number":"pith:KR562SSW","schema_version":"1.0","canonical_sha256":"547bed4a56e19fe08d03457f6853f7fcfea673f98e8af8e32150801549667118","source":{"kind":"arxiv","id":"1805.08207","version":2},"attestation_state":"computed","paper":{"title":"Gradient descent in hyperbolic space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Benjamin Wilson, Matthias Leimeister","submitted_at":"2018-05-18T22:15:03Z","abstract_excerpt":"Gradient descent generalises naturally to Riemannian manifolds, and to hyperbolic $n$-space, in particular. Namely, having calculated the gradient at the point on the manifold representing the model parameters, the updated point is obtained by travelling along the geodesic passing in the direction of the gradient. Some recent works employing optimisation in hyperbolic space have not attempted this procedure, however, employing instead various approximations to avoid a calculation that was considered to be too complicated. In this tutorial, we demonstrate that in the hyperboloid model of hyperb"},"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":"1805.08207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-18T22:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"3679f33cb8844b62edf28d5d91c0f7464c2ed94179476cdb4e0e0bc0f6d379fd","abstract_canon_sha256":"0f8a00e5837f7fb905aa9f04ef69ab8234851c7f229aa990b13e4a688e81259d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:20.672398Z","signature_b64":"fl33znUBGdGPuksMiNhCaaObfvD+wX5KR5DGNB6XTEMpHPPwGQpki/mJHJolSsHGeF8prGjxQ2RqTR6IHrz9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"547bed4a56e19fe08d03457f6853f7fcfea673f98e8af8e32150801549667118","last_reissued_at":"2026-05-18T00:08:20.671754Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:20.671754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient descent in hyperbolic space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Benjamin Wilson, Matthias Leimeister","submitted_at":"2018-05-18T22:15:03Z","abstract_excerpt":"Gradient descent generalises naturally to Riemannian manifolds, and to hyperbolic $n$-space, in particular. Namely, having calculated the gradient at the point on the manifold representing the model parameters, the updated point is obtained by travelling along the geodesic passing in the direction of the gradient. Some recent works employing optimisation in hyperbolic space have not attempted this procedure, however, employing instead various approximations to avoid a calculation that was considered to be too complicated. In this tutorial, we demonstrate that in the hyperboloid model of hyperb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08207","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":"1805.08207","created_at":"2026-05-18T00:08:20.671844+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08207v2","created_at":"2026-05-18T00:08:20.671844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08207","created_at":"2026-05-18T00:08:20.671844+00:00"},{"alias_kind":"pith_short_12","alias_value":"KR562SSW4GP6","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KR562SSW4GP6BDID","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KR562SSW","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2410.22068","citing_title":"A Riemannian gradient descent method for optimization on the indefinite Stiefel manifold","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T","json":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T.json","graph_json":"https://pith.science/api/pith-number/KR562SSW4GP6BDIDIV7WQU7X7T/graph.json","events_json":"https://pith.science/api/pith-number/KR562SSW4GP6BDIDIV7WQU7X7T/events.json","paper":"https://pith.science/paper/KR562SSW"},"agent_actions":{"view_html":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T","download_json":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T.json","view_paper":"https://pith.science/paper/KR562SSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08207&json=true","fetch_graph":"https://pith.science/api/pith-number/KR562SSW4GP6BDIDIV7WQU7X7T/graph.json","fetch_events":"https://pith.science/api/pith-number/KR562SSW4GP6BDIDIV7WQU7X7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T/action/storage_attestation","attest_author":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T/action/author_attestation","sign_citation":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T/action/citation_signature","submit_replication":"https://pith.science/pith/KR562SSW4GP6BDIDIV7WQU7X7T/action/replication_record"}},"created_at":"2026-05-18T00:08:20.671844+00:00","updated_at":"2026-05-18T00:08:20.671844+00:00"}