{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4RQC23K7B7GRCPR2FENKTUHZDY","short_pith_number":"pith:4RQC23K7","schema_version":"1.0","canonical_sha256":"e4602d6d5f0fcd113e3a291aa9d0f91e1607c9b24cc9fff00fa9437014632f61","source":{"kind":"arxiv","id":"2201.03727","version":1},"attestation_state":"computed","paper":{"title":"Estimation and Inference with Proxy Data and its Genetic Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Hongzhe Li, Sai Li, T. Tony Cai","submitted_at":"2022-01-11T00:58:58Z","abstract_excerpt":"Existing high-dimensional statistical methods are largely established for analyzing individual-level data. In this work, we study estimation and inference for high-dimensional linear models where we only observe \"proxy data\", which include the marginal statistics and sample covariance matrix that are computed based on different sets of individuals. We develop a rate optimal method for estimation and inference for the regression coefficient vector and its linear functionals based on the proxy data. Moreover, we show the intrinsic limitations in the proxy-data based inference: the minimax optima"},"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":"2201.03727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2022-01-11T00:58:58Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"d4d984e52f49492f43aec9557b045d90a2c3ac98bf4ef5b70d13a5d0c079bcd8","abstract_canon_sha256":"2ad357e7a19ab87eacfbab831e037e64f48d186807e1ea63595fa9ffa430def8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:32.661749Z","signature_b64":"MURr5GT9V7CdVU8SEnTLIfAFKQ+kb1wbwtO8M47HHX8G5spOHsv/bxqRBXq71paT44x/ifgHp+SzLMRylrHZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4602d6d5f0fcd113e3a291aa9d0f91e1607c9b24cc9fff00fa9437014632f61","last_reissued_at":"2026-07-05T03:47:32.661220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:32.661220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimation and Inference with Proxy Data and its Genetic Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Hongzhe Li, Sai Li, T. Tony Cai","submitted_at":"2022-01-11T00:58:58Z","abstract_excerpt":"Existing high-dimensional statistical methods are largely established for analyzing individual-level data. In this work, we study estimation and inference for high-dimensional linear models where we only observe \"proxy data\", which include the marginal statistics and sample covariance matrix that are computed based on different sets of individuals. We develop a rate optimal method for estimation and inference for the regression coefficient vector and its linear functionals based on the proxy data. Moreover, we show the intrinsic limitations in the proxy-data based inference: the minimax optima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03727","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.03727/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":"2201.03727","created_at":"2026-07-05T03:47:32.661290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03727v1","created_at":"2026-07-05T03:47:32.661290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03727","created_at":"2026-07-05T03:47:32.661290+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RQC23K7B7GR","created_at":"2026-07-05T03:47:32.661290+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RQC23K7B7GRCPR2","created_at":"2026-07-05T03:47:32.661290+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RQC23K7","created_at":"2026-07-05T03:47:32.661290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY","json":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY.json","graph_json":"https://pith.science/api/pith-number/4RQC23K7B7GRCPR2FENKTUHZDY/graph.json","events_json":"https://pith.science/api/pith-number/4RQC23K7B7GRCPR2FENKTUHZDY/events.json","paper":"https://pith.science/paper/4RQC23K7"},"agent_actions":{"view_html":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY","download_json":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY.json","view_paper":"https://pith.science/paper/4RQC23K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03727&json=true","fetch_graph":"https://pith.science/api/pith-number/4RQC23K7B7GRCPR2FENKTUHZDY/graph.json","fetch_events":"https://pith.science/api/pith-number/4RQC23K7B7GRCPR2FENKTUHZDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY/action/storage_attestation","attest_author":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY/action/author_attestation","sign_citation":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY/action/citation_signature","submit_replication":"https://pith.science/pith/4RQC23K7B7GRCPR2FENKTUHZDY/action/replication_record"}},"created_at":"2026-07-05T03:47:32.661290+00:00","updated_at":"2026-07-05T03:47:32.661290+00:00"}