{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SUVMQQWVZZNM7Q6FSHLUEG6OXY","short_pith_number":"pith:SUVMQQWV","schema_version":"1.0","canonical_sha256":"952ac842d5ce5acfc3c591d7421bcebe2ce7e820f42e8be4be931a74c97c2f42","source":{"kind":"arxiv","id":"1703.00864","version":5},"attestation_state":"computed","paper":{"title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ML","authors_text":"Adrian Weller, Krzysztof Choromanski, Mark Rowland","submitted_at":"2017-03-02T17:33:58Z","abstract_excerpt":"We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the Johnson-Lindenstrauss transform and the angular kernel, we show that we can select matrices yielding guaranteed improved performance in accuracy and/or speed compared to earlier methods. We introduce matrices with complex entries which give significant further accuracy improvement. We provide geometric and Markov chain-based perspectives to help understand the benefits, and "},"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":"1703.00864","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-02T17:33:58Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"73611bfe96044cba176c29ccd8e467f2156ecd7dd009b2655229b24f240c7458","abstract_canon_sha256":"ff2f8f0934e6ec537f616c7ff8da25d0968d62e655b5a53c13db10df99f2ee40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:42.084238Z","signature_b64":"TiBPprNakZIdU9R1o+1foWhrwE0/ua6TeiM7aX4uM0rn3RogwQuRgoC894+xSHTeTxjbEUEi+t8CBYuJkz1uCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"952ac842d5ce5acfc3c591d7421bcebe2ce7e820f42e8be4be931a74c97c2f42","last_reissued_at":"2026-05-18T00:06:42.083764Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:42.083764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ML","authors_text":"Adrian Weller, Krzysztof Choromanski, Mark Rowland","submitted_at":"2017-03-02T17:33:58Z","abstract_excerpt":"We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the Johnson-Lindenstrauss transform and the angular kernel, we show that we can select matrices yielding guaranteed improved performance in accuracy and/or speed compared to earlier methods. We introduce matrices with complex entries which give significant further accuracy improvement. We provide geometric and Markov chain-based perspectives to help understand the benefits, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00864","kind":"arxiv","version":5},"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":"1703.00864","created_at":"2026-05-18T00:06:42.083837+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00864v5","created_at":"2026-05-18T00:06:42.083837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00864","created_at":"2026-05-18T00:06:42.083837+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUVMQQWVZZNM","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUVMQQWVZZNM7Q6F","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUVMQQWV","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23418","citing_title":"Approximating Uniform Random Rotations by Two-Block Structured Hadamard Rotations in High Dimensions","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY","json":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY.json","graph_json":"https://pith.science/api/pith-number/SUVMQQWVZZNM7Q6FSHLUEG6OXY/graph.json","events_json":"https://pith.science/api/pith-number/SUVMQQWVZZNM7Q6FSHLUEG6OXY/events.json","paper":"https://pith.science/paper/SUVMQQWV"},"agent_actions":{"view_html":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY","download_json":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY.json","view_paper":"https://pith.science/paper/SUVMQQWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00864&json=true","fetch_graph":"https://pith.science/api/pith-number/SUVMQQWVZZNM7Q6FSHLUEG6OXY/graph.json","fetch_events":"https://pith.science/api/pith-number/SUVMQQWVZZNM7Q6FSHLUEG6OXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY/action/storage_attestation","attest_author":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY/action/author_attestation","sign_citation":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY/action/citation_signature","submit_replication":"https://pith.science/pith/SUVMQQWVZZNM7Q6FSHLUEG6OXY/action/replication_record"}},"created_at":"2026-05-18T00:06:42.083837+00:00","updated_at":"2026-05-18T00:06:42.083837+00:00"}