{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZTXGJRCRDMOWXNID2D7MGUQQ5Q","short_pith_number":"pith:ZTXGJRCR","schema_version":"1.0","canonical_sha256":"ccee64c4511b1d6bb503d0fec35210ec1c5666013b1cd9cd456b44667f8d8400","source":{"kind":"arxiv","id":"2602.14656","version":2},"attestation_state":"computed","paper":{"title":"An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.DG","math.OC"],"primary_cat":"cs.LG","authors_text":"Adri\\'an Javaloy, Antonio Vergari","submitted_at":"2026-02-16T11:27:04Z","abstract_excerpt":"Orthogonality constraints are ubiquitous in robust and probabilistic machine learning. Unfortunately, current optimizers are computationally expensive and do not scale to problems with hundreds or thousands of constraints. One notable exception is the Landing algorithm (Ablin et al., 2024) which, however comes at the expense of temporarily relaxing orthogonality. In this work, we revisit and improve on the ideas behind Landing, enabling the inclusion of modern adaptive optimizers while ensuring that orthogonal constraints are effectively met. Remarkably, these improvements come at little to no"},"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":"2602.14656","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T11:27:04Z","cross_cats_sorted":["math.DG","math.OC"],"title_canon_sha256":"6ab7b43e8429eaba0fa09a1206b554256c2ba05c3f4ed2d0d7b34aa81a670c76","abstract_canon_sha256":"a6e0a1b10c09a1f61dbfcbca8a1e0d861e1723b70ed485968e937aa48d671c4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:17.970347Z","signature_b64":"C1wxdl6Wwn+zLrR2od9XFT0zOzmdgnTc1NdTT8iv8W99yOEwSq0VBJyfurwqVxIzFur0wWIY2+YmAmNVHtRLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccee64c4511b1d6bb503d0fec35210ec1c5666013b1cd9cd456b44667f8d8400","last_reissued_at":"2026-07-20T02:19:17.969378Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:17.969378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.DG","math.OC"],"primary_cat":"cs.LG","authors_text":"Adri\\'an Javaloy, Antonio Vergari","submitted_at":"2026-02-16T11:27:04Z","abstract_excerpt":"Orthogonality constraints are ubiquitous in robust and probabilistic machine learning. Unfortunately, current optimizers are computationally expensive and do not scale to problems with hundreds or thousands of constraints. One notable exception is the Landing algorithm (Ablin et al., 2024) which, however comes at the expense of temporarily relaxing orthogonality. In this work, we revisit and improve on the ideas behind Landing, enabling the inclusion of modern adaptive optimizers while ensuring that orthogonal constraints are effectively met. Remarkably, these improvements come at little to no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14656","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.14656/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":"2602.14656","created_at":"2026-07-20T02:19:17.969845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14656v2","created_at":"2026-07-20T02:19:17.969845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14656","created_at":"2026-07-20T02:19:17.969845+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTXGJRCRDMOW","created_at":"2026-07-20T02:19:17.969845+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTXGJRCRDMOWXNID","created_at":"2026-07-20T02:19:17.969845+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTXGJRCR","created_at":"2026-07-20T02:19:17.969845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.02838","citing_title":"A second-order method landing on the Stiefel manifold via Newton$\\unicode{x2013}$Schulz iteration","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q","json":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q.json","graph_json":"https://pith.science/api/pith-number/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/graph.json","events_json":"https://pith.science/api/pith-number/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/events.json","paper":"https://pith.science/paper/ZTXGJRCR"},"agent_actions":{"view_html":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q","download_json":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q.json","view_paper":"https://pith.science/paper/ZTXGJRCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14656&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/action/storage_attestation","attest_author":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/action/author_attestation","sign_citation":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/action/citation_signature","submit_replication":"https://pith.science/pith/ZTXGJRCRDMOWXNID2D7MGUQQ5Q/action/replication_record"}},"created_at":"2026-07-20T02:19:17.969845+00:00","updated_at":"2026-07-20T02:19:17.969845+00:00"}