{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VCTTDJQZ4HOX6MYUCHIDFUFPKV","short_pith_number":"pith:VCTTDJQZ","schema_version":"1.0","canonical_sha256":"a8a731a619e1dd7f331411d032d0af554414947a62afd326b778f628b5981e66","source":{"kind":"arxiv","id":"1808.03374","version":1},"attestation_state":"computed","paper":{"title":"Fast computation of the principal components of genotype matrices in Julia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","q-bio.GN","stat.AP"],"primary_cat":"math.NA","authors_text":"Alan Edelman, Andreas Noack, Jiahao Chen","submitted_at":"2018-08-09T23:47:21Z","abstract_excerpt":"Finding the largest few principal components of a matrix of genetic data is a common task in genome-wide association studies (GWASs), both for dimensionality reduction and for identifying unwanted factors of variation. We describe a simple random matrix model for matrices that arise in GWASs, showing that the singular values have a bulk behavior that obeys a Marchenko-Pastur distributed with a handful of large outliers. We also implement Golub-Kahan-Lanczos (GKL) bidiagonalization in the Julia programming language, providing thick restarting and a choice between full and partial reorthogonaliz"},"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":"1808.03374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-08-09T23:47:21Z","cross_cats_sorted":["cs.CE","q-bio.GN","stat.AP"],"title_canon_sha256":"79361f535c7d2940ffc9362f08b72e0c221ca4a2a350a7eae089bebbce41704e","abstract_canon_sha256":"e4dd22a760bda7123f851344175290af1699ef47460b1cefb439c3d3ca90525e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:25.244736Z","signature_b64":"aSWB8Jm96TYVhPgEtB+QlJ2dfz54bWUs/Mf+oodFUaH7/9mzj4kniNfnvW5MwH46aiIYBXUt3ajzxi6/eIgDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a731a619e1dd7f331411d032d0af554414947a62afd326b778f628b5981e66","last_reissued_at":"2026-05-18T00:08:25.244131Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:25.244131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast computation of the principal components of genotype matrices in Julia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","q-bio.GN","stat.AP"],"primary_cat":"math.NA","authors_text":"Alan Edelman, Andreas Noack, Jiahao Chen","submitted_at":"2018-08-09T23:47:21Z","abstract_excerpt":"Finding the largest few principal components of a matrix of genetic data is a common task in genome-wide association studies (GWASs), both for dimensionality reduction and for identifying unwanted factors of variation. We describe a simple random matrix model for matrices that arise in GWASs, showing that the singular values have a bulk behavior that obeys a Marchenko-Pastur distributed with a handful of large outliers. We also implement Golub-Kahan-Lanczos (GKL) bidiagonalization in the Julia programming language, providing thick restarting and a choice between full and partial reorthogonaliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03374","kind":"arxiv","version":1},"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":"1808.03374","created_at":"2026-05-18T00:08:25.244225+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03374v1","created_at":"2026-05-18T00:08:25.244225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03374","created_at":"2026-05-18T00:08:25.244225+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCTTDJQZ4HOX","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCTTDJQZ4HOX6MYU","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCTTDJQZ","created_at":"2026-05-18T12:32:59.047623+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/VCTTDJQZ4HOX6MYUCHIDFUFPKV","json":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV.json","graph_json":"https://pith.science/api/pith-number/VCTTDJQZ4HOX6MYUCHIDFUFPKV/graph.json","events_json":"https://pith.science/api/pith-number/VCTTDJQZ4HOX6MYUCHIDFUFPKV/events.json","paper":"https://pith.science/paper/VCTTDJQZ"},"agent_actions":{"view_html":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV","download_json":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV.json","view_paper":"https://pith.science/paper/VCTTDJQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03374&json=true","fetch_graph":"https://pith.science/api/pith-number/VCTTDJQZ4HOX6MYUCHIDFUFPKV/graph.json","fetch_events":"https://pith.science/api/pith-number/VCTTDJQZ4HOX6MYUCHIDFUFPKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV/action/storage_attestation","attest_author":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV/action/author_attestation","sign_citation":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV/action/citation_signature","submit_replication":"https://pith.science/pith/VCTTDJQZ4HOX6MYUCHIDFUFPKV/action/replication_record"}},"created_at":"2026-05-18T00:08:25.244225+00:00","updated_at":"2026-05-18T00:08:25.244225+00:00"}