{"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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005928112,0.0001846322,0.0002538445,0.0007211536,0.0003798536,0.000414083,0.002102714,0.0001777092,0.000008071623],"category_scores_gemma":[0.003026703,0.0001400519,0.00006542086,0.001123096,0.0001226351,0.0002362161,0.004828581,0.00283045,0.00002073726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001653883,"about_ca_system_score_gemma":0.0003116936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006238045,"about_ca_topic_score_gemma":0.0007922417,"domain_scores_codex":[0.9946669,0.001952187,0.0004535981,0.0007252481,0.001749639,0.0004524073],"domain_scores_gemma":[0.9970161,0.001130817,0.000228523,0.001319856,0.0002244438,0.00008024523],"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":[0.0001505267,0.00080199,0.5343903,0.004569486,0.0002889205,0.0004260946,0.01320074,0.3661631,0.003648727,0.004768522,0.006527437,0.06506413],"study_design_scores_gemma":[0.0002499777,0.0001032713,0.21907,0.0008872552,0.00001166175,0.00002161041,0.0004190433,0.7762718,0.0001678361,0.0003653391,0.002255475,0.0001767173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9185212,0.001898645,0.05618016,0.003856589,0.000915541,0.002819287,0.01486404,0.0007788076,0.0001656826],"genre_scores_gemma":[0.9908228,0.0002007495,0.001414928,0.000005881511,0.0001219666,0.00007621186,0.007280846,0.00002419344,0.00005240965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4101087,"threshold_uncertainty_score":0.9994701,"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."}}