{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J5PYL336GC3WKNSJZ4KV3BFGK7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38b49848ef8df15831e32d536568fa8267d462b5bcec103949d8226a5bcce2ed","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2021-05-04T03:08:51Z","title_canon_sha256":"50affdb117890649d7760f0a05a4db2fc69344a6b29eafe7aec712dcad875748"},"schema_version":"1.0","source":{"id":"2105.01264","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.01264","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2105.01264v1","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01264","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"J5PYL336GC3W","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"J5PYL336GC3WKNSJ","created_at":"2026-07-05T02:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"J5PYL336","created_at":"2026-07-05T02:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:7cb67ac107a8e0c99b6fb2d663f8dd564334caca46afd18c632c37289d820bd9","target":"graph","created_at":"2026-07-05T02:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.01264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jue Hou, Tianxi Cai, Zijian Guo","cross_cats":["stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2021-05-04T03:08:51Z","title":"Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01264","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:294a0a1053569ed08f8811a28ae94b26b6f916f54d0ba443d9695645af89bea8","target":"record","created_at":"2026-07-05T02:37:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"38b49848ef8df15831e32d536568fa8267d462b5bcec103949d8226a5bcce2ed","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2021-05-04T03:08:51Z","title_canon_sha256":"50affdb117890649d7760f0a05a4db2fc69344a6b29eafe7aec712dcad875748"},"schema_version":"1.0","source":{"id":"2105.01264","kind":"arxiv","version":1}},"canonical_sha256":"4f5f85ef7e30b7653649cf155d84a657c865078919612f369760a738bb796c8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f5f85ef7e30b7653649cf155d84a657c865078919612f369760a738bb796c8b","first_computed_at":"2026-07-05T02:37:15.268822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:15.268822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+1HcnxAGc9SYPFZmcYvnyuMoZCyBAI3SzCpBs0aHYYWbcSLqqe75FI0IiRvUR6DJXchVJ+xMlaSmPcH1zLHwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:15.269235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.01264","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:294a0a1053569ed08f8811a28ae94b26b6f916f54d0ba443d9695645af89bea8","sha256:7cb67ac107a8e0c99b6fb2d663f8dd564334caca46afd18c632c37289d820bd9"],"state_sha256":"35cd2e118dcf6110574a893ccb4334f3a1d7254399bd2b761b3ad817480d310f"}