{"id":"W4388933883","doi":"10.21203/rs.3.rs-3626886/v1","title":"Measuring the Prediction Difficulty of Individual Cases in a Dataset using Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Machine learning; Metric (unit); Artificial intelligence; Artificial neural network; Data mining; Key (lock); Perspective (graphical); Predictive modelling; Variety (cybernetics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0112341,0.001681123,0.001292843,0.00685442,0.000951488,0.004090186,0.001850451,0.002259777,0.001727278],"category_scores_gemma":[0.08053892,0.000286055,0.001460576,0.00522626,0.001190893,0.005136472,0.001903478,0.003033504,0.0008932784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001744624,"about_ca_system_score_gemma":0.001296181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002927987,"about_ca_topic_score_gemma":0.004063834,"domain_scores_codex":[0.9889861,0.003044756,0.002029407,0.002033322,0.003472237,0.0004341904],"domain_scores_gemma":[0.8876022,0.08139897,0.009686186,0.01043733,0.008911364,0.00196398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009789416,0.0008412189,0.4896417,0.001605736,0.001105415,0.0006805009,0.0006827482,0.2276516,0.005160499,0.00819331,0.03942542,0.224033],"study_design_scores_gemma":[0.00005487341,0.0004062605,0.09557325,0.0003179058,0.0001705723,0.0006670927,0.0007868304,0.8435928,0.009805361,0.03863721,0.009797284,0.000190663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7281141,0.003244794,0.2209898,0.004989509,0.000880553,0.0007898014,0.0257878,0.004249867,0.01095371],"genre_scores_gemma":[0.8681438,0.0005341657,0.09813224,0.000357706,0.0002721621,0.0003982211,0.03079461,0.0002109051,0.001156064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0112341,"threshold_uncertainty_score":0.05941224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3075164299209969,"score_gpt":0.4225685595853316,"score_spread":0.1150521296643348,"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."}}