{"id":"W4389728957","doi":"10.21203/rs.3.rs-3736323/v1","title":"Prediction Performance Metrics Considering the Difficulty of Individual Cases","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Metric (unit); Performance prediction; Performance metric; Artificial intelligence; Predictive modelling; Artificial neural network; Variety (cybernetics); Data mining; Simulation; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.004089491,0.0001413891,0.0001882396,0.0005983823,0.0003927901,0.0003940057,0.00189432,0.0001651724,0.000007638457],"category_scores_gemma":[0.002839525,0.00009975444,0.00007491017,0.001378989,0.0001664202,0.0001845266,0.003655812,0.001587606,0.00005185829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008491927,"about_ca_system_score_gemma":0.0003225423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000280445,"about_ca_topic_score_gemma":0.00002550322,"domain_scores_codex":[0.996385,0.0006275579,0.0003365821,0.0005317195,0.001763463,0.0003556968],"domain_scores_gemma":[0.9960496,0.0018006,0.0001809485,0.00138964,0.0005020839,0.00007711578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007451834,0.0006105356,0.3376642,0.008131634,0.0004685605,0.0001335469,0.01410106,0.06063097,0.0006459251,0.03450841,0.05820536,0.4848253],"study_design_scores_gemma":[0.0001690257,0.0002184234,0.6962333,0.0005343329,0.00001439284,0.00002033581,0.0004845196,0.2956598,0.0004964648,0.0006822137,0.005306984,0.000180154],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9416409,0.001195766,0.04579402,0.005420852,0.001376653,0.001688004,0.0008252249,0.0009004458,0.001158147],"genre_scores_gemma":[0.9970806,0.0006126409,0.001479268,0.000008558864,0.000141963,0.0001090829,0.0002852778,0.00001498224,0.0002676544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4846451,"threshold_uncertainty_score":0.6897445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2739598167954957,"score_gpt":0.4073426254268437,"score_spread":0.133382808631348,"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."}}