{"id":"W4412960886","doi":"10.1101/2025.07.15.25331536","title":"VALORIS: A privacy-aware logistic regression method for vertically partitioned data within a novel privacy risk assessment framework","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut des maladies génétiques Imagine; Agence Nationale de la Recherche; Université de Sherbrooke","keywords":"Logistic regression; Computer science; Inference; Information privacy; Statistical inference; Data mining; Analytics; Variable (mathematics); Data science; Internet privacy; Statistics; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005573652,0.0007040297,0.001380802,0.0001584416,0.0004007298,0.0003127755,0.002513067,0.0009217467,0.0001606564],"category_scores_gemma":[0.1073963,0.0005485706,0.0002449889,0.0002840609,0.0001784916,0.0001010228,0.004771613,0.002299602,0.00001005652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002294041,"about_ca_system_score_gemma":0.001036875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009187329,"about_ca_topic_score_gemma":0.0000249989,"domain_scores_codex":[0.9941148,0.001082682,0.001536218,0.001767803,0.0008632003,0.0006352899],"domain_scores_gemma":[0.9750286,0.01838688,0.001057257,0.004580593,0.0006515309,0.0002951232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003994432,0.001334885,0.004923611,0.006135219,0.0008849616,0.00002714388,0.001400701,0.0002125665,0.0001795783,0.9643225,0.006131909,0.01404746],"study_design_scores_gemma":[0.0005334828,0.0001152855,0.002230519,0.002900002,0.0008769918,0.000002207538,0.00003873787,0.2456123,0.0001608525,0.7462461,0.0008005772,0.0004829524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001176259,0.00006773819,0.9888882,0.001217077,0.001687163,0.002052382,0.004325518,0.0002731508,0.0003124858],"genre_scores_gemma":[0.02270288,0.00006699518,0.9751335,0.0002339196,0.0003383941,0.0008893745,0.0003809655,0.00007289657,0.000181098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2453998,"threshold_uncertainty_score":0.9996966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3100622355650619,"score_gpt":0.5096453187814506,"score_spread":0.1995830832163887,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}