{"id":"W2966262171","doi":"","title":"Reproducibility in Machine Learning for Health","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Field (mathematics); Reproducibility; Machine learning; Scale (ratio); Artificial intelligence; Data science; Human health; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.001786499,0.0001387795,0.0001959412,0.0003109144,0.0001800866,0.000244988,0.000822329,0.00004706817,0.0002963558],"category_scores_gemma":[0.002490199,0.0001490142,0.00008144734,0.0003698334,0.00003674125,0.0005762472,0.0001766974,0.0004745653,0.0003323602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001939276,"about_ca_system_score_gemma":0.0001991486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007190017,"about_ca_topic_score_gemma":0.000210899,"domain_scores_codex":[0.9972726,0.0002597478,0.0004683511,0.00129925,0.0003858019,0.0003142259],"domain_scores_gemma":[0.9979575,0.0004835168,0.0002399813,0.000899038,0.0003421408,0.00007777596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008671122,0.0002622262,0.2028249,0.0000282133,0.00003372753,0.000006747331,0.005980202,0.1112167,0.002268328,0.6442588,0.000271284,0.03276218],"study_design_scores_gemma":[0.0003811439,0.0003594693,0.02218014,0.000081828,0.000001352544,0.00000574378,0.0008062394,0.9491829,0.001757704,0.01675257,0.008263385,0.0002275199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3815531,0.00009703071,0.4541762,0.07863376,0.002760839,0.002455533,0.00001680848,0.0007883348,0.0795184],"genre_scores_gemma":[0.9870693,0.00003059558,0.004501123,0.0003653475,0.0000571588,0.00009942318,0.00005191075,0.00001278451,0.007812345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8379661,"threshold_uncertainty_score":0.6076622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.088447391195338,"score_gpt":0.3988270749660196,"score_spread":0.3103796837706816,"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."}}