{"id":"W4392297233","doi":"10.3390/eng5010021","title":"Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data","year":2024,"lang":"en","type":"article","venue":"Eng—Advances in Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Fusion (Canada)","funders":"","keywords":"Categorical variable; Workflow; Computer science; Machine learning; Artificial intelligence; Supervised learning; Data science; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002359731,0.0001168548,0.0001510618,0.0001154138,0.00003495411,0.00008885101,0.0003164416,0.00002650985,0.000002331412],"category_scores_gemma":[0.00005986804,0.0000974321,0.00000759607,0.0002810544,0.00002863733,0.000753719,0.0003420252,0.0002981872,0.000001057013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002045607,"about_ca_system_score_gemma":0.00001101241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002935158,"about_ca_topic_score_gemma":0.000006788907,"domain_scores_codex":[0.9991152,0.00003247228,0.0001711479,0.0003791695,0.0001505809,0.0001514798],"domain_scores_gemma":[0.9994442,0.0001824839,0.00002619909,0.0002854942,0.000006845089,0.0000547481],"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":[0.00005875053,0.0001441438,0.2066594,0.001395651,0.00006903132,0.0001415629,0.002649063,0.2797958,0.005563287,0.06669283,0.000006991831,0.4368235],"study_design_scores_gemma":[0.0001737833,0.00004580258,0.01243751,0.0001045812,0.000003636367,0.00003218142,0.00001684723,0.965425,0.00003757904,0.00002120323,0.02158894,0.0001129481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1073788,0.01539133,0.8764014,0.0001956736,0.0001693871,0.00009852913,0.000009104993,0.0002066266,0.0001491809],"genre_scores_gemma":[0.9522188,0.0007254565,0.04693772,0.000004116785,0.00002622943,0.000005195215,0.00005360013,0.00001122193,0.00001772298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.84484,"threshold_uncertainty_score":0.3973166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02318533791175964,"score_gpt":0.2550979615735789,"score_spread":0.2319126236618193,"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."}}