{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:546OZUGW5WL24UGPTR7UKHWYKE","short_pith_number":"pith:546OZUGW","schema_version":"1.0","canonical_sha256":"ef3cecd0d6ed97ae50cf9c7f451ed8510dd3ff7a9a9afbc4e1f9dcc743e89e9c","source":{"kind":"arxiv","id":"2107.12365","version":2},"attestation_state":"computed","paper":{"title":"Inference for Heteroskedastic PCA with Missing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Yuling Yan, Yuxin Chen","submitted_at":"2021-07-26T17:59:01Z","abstract_excerpt":"This paper studies how to construct confidence regions for principal component analysis (PCA) in high dimension, a problem that has been vastly under-explored. While computing measures of uncertainty for nonlinear/nonconvex estimators is in general difficult in high dimension, the challenge is further compounded by the prevalent presence of missing data and heteroskedastic noise. We propose a novel approach to performing valid inference on the principal subspace under a spiked covariance model with missing data, on the basis of an estimator called HeteroPCA (Zhang et al., 2022). We develop non"},"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":"2107.12365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2021-07-26T17:59:01Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"61f77addfb28a397f8d97f18d53f77753bf038d73ff5f7a535c154acb71217e6","abstract_canon_sha256":"fbf09805c6eb286df7e9d9140371bbc9b65e2f6062c5cc7e274fc37fdb1dd494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:37.623629Z","signature_b64":"SIFEQrlqeDUBr3LhR70TveWV4G9c2sCv985tt4acVGMyKywBMfmIdTK2kwhunJQQvrazDWxHTK1imYQIHTLRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3cecd0d6ed97ae50cf9c7f451ed8510dd3ff7a9a9afbc4e1f9dcc743e89e9c","last_reissued_at":"2026-07-05T10:31:37.622887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:37.622887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference for Heteroskedastic PCA with Missing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Yuling Yan, Yuxin Chen","submitted_at":"2021-07-26T17:59:01Z","abstract_excerpt":"This paper studies how to construct confidence regions for principal component analysis (PCA) in high dimension, a problem that has been vastly under-explored. While computing measures of uncertainty for nonlinear/nonconvex estimators is in general difficult in high dimension, the challenge is further compounded by the prevalent presence of missing data and heteroskedastic noise. We propose a novel approach to performing valid inference on the principal subspace under a spiked covariance model with missing data, on the basis of an estimator called HeteroPCA (Zhang et al., 2022). We develop non"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12365","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/2107.12365/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":"2107.12365","created_at":"2026-07-05T10:31:37.622959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12365v2","created_at":"2026-07-05T10:31:37.622959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12365","created_at":"2026-07-05T10:31:37.622959+00:00"},{"alias_kind":"pith_short_12","alias_value":"546OZUGW5WL2","created_at":"2026-07-05T10:31:37.622959+00:00"},{"alias_kind":"pith_short_16","alias_value":"546OZUGW5WL24UGP","created_at":"2026-07-05T10:31:37.622959+00:00"},{"alias_kind":"pith_short_8","alias_value":"546OZUGW","created_at":"2026-07-05T10:31:37.622959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.02480","citing_title":"Statistical Inference for Linear Functions of Eigenvectors with Small Eigengaps","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE","json":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE.json","graph_json":"https://pith.science/api/pith-number/546OZUGW5WL24UGPTR7UKHWYKE/graph.json","events_json":"https://pith.science/api/pith-number/546OZUGW5WL24UGPTR7UKHWYKE/events.json","paper":"https://pith.science/paper/546OZUGW"},"agent_actions":{"view_html":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE","download_json":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE.json","view_paper":"https://pith.science/paper/546OZUGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12365&json=true","fetch_graph":"https://pith.science/api/pith-number/546OZUGW5WL24UGPTR7UKHWYKE/graph.json","fetch_events":"https://pith.science/api/pith-number/546OZUGW5WL24UGPTR7UKHWYKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE/action/storage_attestation","attest_author":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE/action/author_attestation","sign_citation":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE/action/citation_signature","submit_replication":"https://pith.science/pith/546OZUGW5WL24UGPTR7UKHWYKE/action/replication_record"}},"created_at":"2026-07-05T10:31:37.622959+00:00","updated_at":"2026-07-05T10:31:37.622959+00:00"}