{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4609308,0.001360204,0.003361754,0.008808844,0.004230001,0.02047279,0.006945753,0.005893373,0.01025856],"category_scores_gemma":[0.8098052,0.001540337,0.003979392,0.009165728,0.02012133,0.01848185,0.01279689,0.008120709,0.003726515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005418624,"about_ca_system_score_gemma":0.01611867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001973735,"about_ca_topic_score_gemma":0.001443039,"domain_scores_codex":[0.4879948,0.3565743,0.04082423,0.03209327,0.07976238,0.002750929],"domain_scores_gemma":[0.07676753,0.6981449,0.02725886,0.1577353,0.03817299,0.001920545],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001736158,0.0003718343,0.0529915,0.01507469,0.004242722,0.0006110572,0.009603457,0.01059423,0.00230904,0.2839007,0.04954547,0.5690191],"study_design_scores_gemma":[0.0006588788,0.001141802,0.02577298,0.01055612,0.001687618,0.001127398,0.002409906,0.02145392,0.01304608,0.6874776,0.2341982,0.000469326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.04686713,0.0867136,0.6601108,0.1125983,0.0139036,0.002909661,0.006030561,0.00539396,0.06547231],"genre_scores_gemma":[0.6441832,0.01378927,0.2882324,0.02092542,0.01011424,0.005556368,0.005322288,0.003079429,0.008797452],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.5390692,"threshold_uncertainty_score":0.6647683,"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."}}