{"id":"W4411530865","doi":"10.21203/rs.3.rs-6933988/v1","title":"Revisiting VERTIGO and VERTIGO-CI:  Identifying confidentiality breaches and introducing a statistically sound, efficient alternative","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Interpretability; Vertigo; Computer science; Term (time); Logistic regression; Confidence interval; Data mining; Medicine; Machine learning; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.006121822,0.000390105,0.0008341093,0.000372119,0.0005195047,0.0009096766,0.0004079692,0.0002653881,0.0001432245],"category_scores_gemma":[0.02669008,0.0003646058,0.0000952726,0.0002723044,0.0006680572,0.0000555314,0.002896237,0.001996782,0.000009278504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002716695,"about_ca_system_score_gemma":0.0002751092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001059732,"about_ca_topic_score_gemma":0.00003753843,"domain_scores_codex":[0.9937634,0.002072872,0.0008391552,0.001263773,0.001277574,0.0007832085],"domain_scores_gemma":[0.9855987,0.01207658,0.0002131635,0.0007344326,0.001047599,0.0003295149],"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":[0.0002575122,0.0002303203,0.007145969,0.02896941,0.0004760559,0.000104954,0.0104277,0.00008263589,0.000415487,0.8389602,0.0006222217,0.1123075],"study_design_scores_gemma":[0.0005831182,0.00009928391,0.008223894,0.006558177,0.0001463567,0.00001210833,0.002654335,0.03377433,0.0007076647,0.946651,0.00007680171,0.0005129285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2444473,0.001382293,0.7500755,0.0002895131,0.0002798526,0.00125583,0.0008175603,0.0000829739,0.00136918],"genre_scores_gemma":[0.7738718,0.0004401846,0.2248151,0.00003537538,0.0004212474,0.0001544442,0.00004004057,0.00004373961,0.0001780203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5294245,"threshold_uncertainty_score":0.9998806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1912190167844339,"score_gpt":0.4918391326250635,"score_spread":0.3006201158406296,"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."}}