{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J5PYL336GC3WKNSJZ4KV3BFGK7","short_pith_number":"pith:J5PYL336","schema_version":"1.0","canonical_sha256":"4f5f85ef7e30b7653649cf155d84a657c865078919612f369760a738bb796c8b","source":{"kind":"arxiv","id":"2105.01264","version":1},"attestation_state":"computed","paper":{"title":"Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jue Hou, Tianxi Cai, Zijian Guo","submitted_at":"2021-05-04T03:08:51Z","abstract_excerpt":"Risk modeling with EHR data is challenging due to a lack of direct observations on the disease outcome, and the high dimensionality of the candidate predictors. In this paper, we develop a surrogate assisted semi-supervised-learning (SAS) approach to risk modeling with high dimensional predictors, leveraging a large unlabeled data on candidate predictors and surrogates of outcome, as well as a small labeled data with annotated outcomes. The SAS procedure borrows information from surrogates along with candidate predictors to impute the unobserved outcomes via a sparse working imputation model w"},"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":"2105.01264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2021-05-04T03:08:51Z","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"50affdb117890649d7760f0a05a4db2fc69344a6b29eafe7aec712dcad875748","abstract_canon_sha256":"38b49848ef8df15831e32d536568fa8267d462b5bcec103949d8226a5bcce2ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:15.269235Z","signature_b64":"+1HcnxAGc9SYPFZmcYvnyuMoZCyBAI3SzCpBs0aHYYWbcSLqqe75FI0IiRvUR6DJXchVJ+xMlaSmPcH1zLHwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5f85ef7e30b7653649cf155d84a657c865078919612f369760a738bb796c8b","last_reissued_at":"2026-07-05T02:37:15.268822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:15.268822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jue Hou, Tianxi Cai, Zijian Guo","submitted_at":"2021-05-04T03:08:51Z","abstract_excerpt":"Risk modeling with EHR data is challenging due to a lack of direct observations on the disease outcome, and the high dimensionality of the candidate predictors. In this paper, we develop a surrogate assisted semi-supervised-learning (SAS) approach to risk modeling with high dimensional predictors, leveraging a large unlabeled data on candidate predictors and surrogates of outcome, as well as a small labeled data with annotated outcomes. The SAS procedure borrows information from surrogates along with candidate predictors to impute the unobserved outcomes via a sparse working imputation model w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01264","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/2105.01264/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":"2105.01264","created_at":"2026-07-05T02:37:15.268886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01264v1","created_at":"2026-07-05T02:37:15.268886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01264","created_at":"2026-07-05T02:37:15.268886+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5PYL336GC3W","created_at":"2026-07-05T02:37:15.268886+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5PYL336GC3WKNSJ","created_at":"2026-07-05T02:37:15.268886+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5PYL336","created_at":"2026-07-05T02:37:15.268886+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/J5PYL336GC3WKNSJZ4KV3BFGK7","json":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7.json","graph_json":"https://pith.science/api/pith-number/J5PYL336GC3WKNSJZ4KV3BFGK7/graph.json","events_json":"https://pith.science/api/pith-number/J5PYL336GC3WKNSJZ4KV3BFGK7/events.json","paper":"https://pith.science/paper/J5PYL336"},"agent_actions":{"view_html":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7","download_json":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7.json","view_paper":"https://pith.science/paper/J5PYL336","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01264&json=true","fetch_graph":"https://pith.science/api/pith-number/J5PYL336GC3WKNSJZ4KV3BFGK7/graph.json","fetch_events":"https://pith.science/api/pith-number/J5PYL336GC3WKNSJZ4KV3BFGK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7/action/storage_attestation","attest_author":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7/action/author_attestation","sign_citation":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7/action/citation_signature","submit_replication":"https://pith.science/pith/J5PYL336GC3WKNSJZ4KV3BFGK7/action/replication_record"}},"created_at":"2026-07-05T02:37:15.268886+00:00","updated_at":"2026-07-05T02:37:15.268886+00:00"}