{"id":"W4387838655","doi":"10.48550/arxiv.2310.12568","title":"Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Deutsche Forschungsgemeinschaft; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Python (programming language); Computer science; Pipeline (software); Generalization; Artificial intelligence; Open source; Machine learning; Software engineering; Data science; Data mining; Software; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008433768,0.004358958,0.001669234,0.003027733,0.001281882,0.004167129,0.00825722,0.002400947,0.04517864],"category_scores_gemma":[0.04204301,0.002681635,0.003820656,0.002143089,0.00237054,0.007448134,0.007958482,0.006476169,0.03768519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002130659,"about_ca_system_score_gemma":0.006174613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004305995,"about_ca_topic_score_gemma":0.006862152,"domain_scores_codex":[0.9937231,0.001619647,0.0007414399,0.001008014,0.002463315,0.0004445005],"domain_scores_gemma":[0.987058,0.006421169,0.0009533381,0.002860681,0.002214659,0.0004922231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008254679,0.0003529763,0.005824138,0.003266922,0.0004828942,0.0007124044,0.0006893267,0.04918751,0.007470055,0.04032777,0.5511311,0.3397295],"study_design_scores_gemma":[0.0003502015,0.0002138851,0.002217653,0.0006814292,0.0001098428,0.0006642463,0.0001226925,0.5547846,0.03440712,0.1380063,0.2680921,0.0003499571],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00137066,0.0002741362,0.5083755,0.0004491318,0.0002241118,0.0001872142,0.004929726,0.4807855,0.003404093],"genre_scores_gemma":[0.05851365,0.001080267,0.7034514,0.001924731,0.0002550433,0.00185424,0.03595867,0.1849984,0.01196354],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04517864,"threshold_uncertainty_score":0.1511375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2567715085980189,"score_gpt":0.249742154285979,"score_spread":0.007029354312039937,"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."}}