{"id":"W4399615587","doi":"10.1007/s10664-024-10450-y","title":"How far are we with automated machine learning? characterization and challenges of AutoML toolkits","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Characterization (materials science); Computer science; Artificial intelligence; Machine learning; Nanotechnology; Materials science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000147711,0.0001623591,0.0001826813,0.0001524948,0.00005001102,0.0002205696,0.0002013222,0.00007431487,0.000002474381],"category_scores_gemma":[0.0002298417,0.0001303305,0.00002600879,0.000376779,0.00001787129,0.000471032,0.00009986549,0.0002588712,0.00000381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002462309,"about_ca_system_score_gemma":0.00002212603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000332287,"about_ca_topic_score_gemma":0.000001376035,"domain_scores_codex":[0.9990699,0.00004085178,0.0001411332,0.0003669228,0.0002054617,0.0001757852],"domain_scores_gemma":[0.9994222,0.0001688224,0.00006421043,0.0002241948,0.00004121758,0.00007934346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003161925,0.0001813279,0.1223193,0.005054217,0.0002868233,0.0001754786,0.005417316,0.01930754,0.007794795,0.01652607,0.0003328328,0.8225727],"study_design_scores_gemma":[0.00009175236,0.00008491086,0.1507107,0.0002059951,0.000008148154,0.00002643877,0.000008380929,0.768507,0.0001376675,0.00000751171,0.08004882,0.0001626889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02916175,0.004981663,0.952388,0.009592379,0.0001391954,0.00009105576,0.00001138222,0.003626643,0.000007954043],"genre_scores_gemma":[0.9788886,0.001199629,0.01952459,0.00003011988,0.00006344818,0.0000156516,0.0000597159,0.00003227342,0.0001859406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9497269,"threshold_uncertainty_score":0.5314724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02592931027558718,"score_gpt":0.2455855985960089,"score_spread":0.2196562883204217,"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."}}