{"id":"W4367313097","doi":"10.2196/preprints.47995","title":"Reporting and Methodological Observations on Prognostic and Diagnostic Machine Learning Studies (Preprint)","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Preprint; Key (lock); Data science; Computer science; Artificial intelligence; Machine learning; Psychology; World Wide Web; Computer security","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":[0.00522564,0.0003370971,0.00068213,0.0001922737,0.0004178166,0.00040848,0.0005260014,0.0001962491,0.000006191435],"category_scores_gemma":[0.150499,0.0002753876,0.00008064158,0.0003285898,0.0001694953,0.0002032337,0.005107387,0.001036755,0.00003611953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000622147,"about_ca_system_score_gemma":0.00007510298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004014159,"about_ca_topic_score_gemma":0.0001837076,"domain_scores_codex":[0.9960081,0.0005843268,0.001302505,0.001370318,0.0003369954,0.0003977357],"domain_scores_gemma":[0.979504,0.01817897,0.001148148,0.0007406755,0.0002853904,0.000142828],"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":[0.00002055951,0.0002191916,0.5430018,0.001101649,0.0004809606,0.00121154,0.01167454,0.08540286,0.0005003108,0.2584422,0.0004633586,0.09748103],"study_design_scores_gemma":[0.0001015327,0.0004704003,0.2302633,0.001081005,0.0000835219,0.00006800025,0.001779255,0.3966103,0.002204564,0.3660886,0.0003297169,0.0009197693],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5172436,0.001710198,0.4698137,0.007435331,0.000765249,0.001179386,0.000002444918,0.001418877,0.0004311895],"genre_scores_gemma":[0.8073598,0.002241854,0.1884892,0.0003291324,0.00009465712,0.0003680828,0.0000093016,0.00003116889,0.001076858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3127385,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5131537115510197,"score_gpt":0.4383888926787479,"score_spread":0.07476481887227188,"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."}}