{"id":"W4312847312","doi":"10.1109/icsme55016.2022.00014","title":"An Empirical Study on the Usage of Automated Machine Learning Tools","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Empirical research; Artificial intelligence; Machine learning; Data science; Human–computer interaction; Statistics","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":[0.001232584,0.00007364107,0.00009336162,0.00006953019,0.000394049,0.0001036631,0.0009789792,0.00001129904,0.0002287774],"category_scores_gemma":[0.0001557485,0.00004713589,0.00002496122,0.0004375966,0.00001556733,0.0001674063,0.0003171547,0.000343355,0.00002078756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002052553,"about_ca_system_score_gemma":0.00002765099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101186,"about_ca_topic_score_gemma":0.000006725052,"domain_scores_codex":[0.9980557,0.001006608,0.0001722881,0.0002678822,0.0003840878,0.0001134583],"domain_scores_gemma":[0.9988455,0.0003184091,0.00009562277,0.0006847297,0.00002180814,0.00003395927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008539409,0.005139879,0.710793,0.00001162311,0.00008621104,0.0000350696,0.01784408,0.05296146,0.00753133,0.08120926,0.00849135,0.1158113],"study_design_scores_gemma":[0.0001424885,0.0008649396,0.2133044,7.184937e-7,0.000002437371,0.000002906174,0.0005580629,0.7791148,0.0000683654,0.00003996613,0.005839828,0.0000610398],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423221,0.000009096453,0.04462416,0.004110173,0.0001079229,0.0003147293,0.000007317052,0.001096681,0.007407857],"genre_scores_gemma":[0.9981764,3.320248e-7,0.0009406132,0.0003809662,0.000009597801,0.0000266916,0.00002216236,0.000005161157,0.0004380663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7261534,"threshold_uncertainty_score":0.3030747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06111834535786222,"score_gpt":0.3460897599133117,"score_spread":0.2849714145554495,"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."}}