{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005893502,0.0002275394,0.000270382,0.0005482161,0.0001803112,0.0002252458,0.001472849,0.0002253554,0.000008370112],"category_scores_gemma":[0.0002106594,0.0002860132,0.0001106261,0.0008105275,0.00008723947,0.002834053,0.002005657,0.0002497287,0.00002499483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001219594,"about_ca_system_score_gemma":0.0002363395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004352366,"about_ca_topic_score_gemma":0.000200677,"domain_scores_codex":[0.9979803,0.0001990029,0.0002580948,0.001105796,0.0001695374,0.0002872436],"domain_scores_gemma":[0.9975566,0.0002108442,0.0002264647,0.001465176,0.0003594077,0.0001815123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006563578,0.00007062444,0.0005147119,0.00007256067,0.0000357448,0.00001599928,0.0008021824,0.7025384,0.0001406174,0.2935113,0.0005637215,0.001668495],"study_design_scores_gemma":[0.0001326951,0.0001245222,0.000573065,0.00004964391,0.00003450906,6.31943e-7,0.0001667639,0.6675481,0.001460099,0.3296314,0.00008477969,0.0001937889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2801529,0.00001562398,0.7175551,0.0001845239,0.0003761226,0.0008102747,0.00003146279,0.0004939087,0.0003800733],"genre_scores_gemma":[0.9863548,0.0001021887,0.01213515,0.00006997949,0.00006296511,0.000008477361,0.00003397968,0.0000402847,0.001192125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.706202,"threshold_uncertainty_score":0.9999592,"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."}}