{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:4Z3YF5DKQLARZJOU5WEQLCF6Y2","short_pith_number":"pith:4Z3YF5DK","schema_version":"1.0","canonical_sha256":"e67782f46a82c11ca5d4ed890588bec6bccdde323c4d465c27ad5470500d8b46","source":{"kind":"arxiv","id":"1208.4122","version":2},"attestation_state":"computed","paper":{"title":"Principal Component Analysis with Noisy and/or Missing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.data-an"],"primary_cat":"astro-ph.IM","authors_text":"Stephen Bailey","submitted_at":"2012-08-20T20:59:10Z","abstract_excerpt":"We present a method for performing Principal Component Analysis (PCA) on noisy datasets with missing values. Estimates of the measurement error are used to weight the input data such that compared to classic PCA, the resulting eigenvectors are more sensitive to the true underlying signal variations rather than being pulled by heteroskedastic measurement noise. Missing data is simply the limiting case of weight=0. The underlying algorithm is a noise weighted Expectation Maximization (EM) PCA, which has additional benefits of implementation speed and flexibility for smoothing eigenvectors to red"},"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":"1208.4122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"astro-ph.IM","submitted_at":"2012-08-20T20:59:10Z","cross_cats_sorted":["physics.data-an"],"title_canon_sha256":"b19a8be2a439234bdd2b6655920786f2b8a5bc55e134a1fce66b3f96f611c97f","abstract_canon_sha256":"bf92e983093d8d1f5ae1b93da9a54da0461b8a43e4467e40086f81c4c3f2cd7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:09.018803Z","signature_b64":"UZD0ZUQCmzbue299VhBpIUXPDKhQJvODsHYMbHgZ5zSU9Q9+/aQ6TWY5nnZVm+XeR1PHMJM1lZ6DrahoVX9eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67782f46a82c11ca5d4ed890588bec6bccdde323c4d465c27ad5470500d8b46","last_reissued_at":"2026-05-18T01:55:09.018181Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:09.018181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principal Component Analysis with Noisy and/or Missing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.data-an"],"primary_cat":"astro-ph.IM","authors_text":"Stephen Bailey","submitted_at":"2012-08-20T20:59:10Z","abstract_excerpt":"We present a method for performing Principal Component Analysis (PCA) on noisy datasets with missing values. Estimates of the measurement error are used to weight the input data such that compared to classic PCA, the resulting eigenvectors are more sensitive to the true underlying signal variations rather than being pulled by heteroskedastic measurement noise. Missing data is simply the limiting case of weight=0. The underlying algorithm is a noise weighted Expectation Maximization (EM) PCA, which has additional benefits of implementation speed and flexibility for smoothing eigenvectors to red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.4122","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":"1208.4122","created_at":"2026-05-18T01:55:09.018291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.4122v2","created_at":"2026-05-18T01:55:09.018291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.4122","created_at":"2026-05-18T01:55:09.018291+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Z3YF5DKQLAR","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Z3YF5DKQLARZJOU","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Z3YF5DK","created_at":"2026-05-18T12:26:53.410803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08081","citing_title":"Robust Heteroskedastic Matrix Factorization: A Generalization of PCA that Flags Outliers and Handles Missing Data","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2","json":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2.json","graph_json":"https://pith.science/api/pith-number/4Z3YF5DKQLARZJOU5WEQLCF6Y2/graph.json","events_json":"https://pith.science/api/pith-number/4Z3YF5DKQLARZJOU5WEQLCF6Y2/events.json","paper":"https://pith.science/paper/4Z3YF5DK"},"agent_actions":{"view_html":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2","download_json":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2.json","view_paper":"https://pith.science/paper/4Z3YF5DK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.4122&json=true","fetch_graph":"https://pith.science/api/pith-number/4Z3YF5DKQLARZJOU5WEQLCF6Y2/graph.json","fetch_events":"https://pith.science/api/pith-number/4Z3YF5DKQLARZJOU5WEQLCF6Y2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2/action/storage_attestation","attest_author":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2/action/author_attestation","sign_citation":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2/action/citation_signature","submit_replication":"https://pith.science/pith/4Z3YF5DKQLARZJOU5WEQLCF6Y2/action/replication_record"}},"created_at":"2026-05-18T01:55:09.018291+00:00","updated_at":"2026-05-18T01:55:09.018291+00:00"}