{"id":"W4299285432","doi":"10.1016/j.conbuildmat.2022.129227","title":"Explainable machine learning models for predicting the axial compression capacity of concrete filled steel tubular columns","year":2022,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Structural Load-Bearing Analysis","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Gradient boosting; Categorical variable; Structural engineering; Boosting (machine learning); AdaBoost; Machine learning; Compression (physics); Computer science; Random forest; Artificial intelligence; Compressive strength; Engineering; Mathematics; Support vector machine; Materials science; Composite material","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006348257,0.0006985163,0.0003971375,0.0005272396,0.0002546978,0.000536871,0.0008013063,0.001109034,0.0014707],"category_scores_gemma":[0.00283009,0.0003701282,0.0005699641,0.0003879816,0.0005014739,0.0007494786,0.0003746145,0.0009936156,0.0002138721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008554441,"about_ca_system_score_gemma":0.0004879403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01361109,"about_ca_topic_score_gemma":0.01402898,"domain_scores_codex":[0.9998578,0.00004897399,0.000008903283,0.00004008459,0.00002168427,0.00002244647],"domain_scores_gemma":[0.9981928,0.001442684,0.0001596389,0.00005941236,0.000121497,0.00002384994],"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":[0.00001736658,0.00001392725,0.0007384931,0.000008406966,0.00001011507,0.00001526672,0.00001287128,0.9942765,0.0002425355,0.001039751,0.0001509182,0.003473763],"study_design_scores_gemma":[0.000001206133,0.000002468857,0.0001450914,6.850428e-7,0.000001419958,0.000001215303,0.000001044522,0.9991405,0.00004552793,0.0006423675,0.00001758581,9.158489e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5550404,0.0007319426,0.4394816,0.0006638919,0.00006585386,0.00004253378,0.001122442,0.0009253407,0.00192587],"genre_scores_gemma":[0.9884431,0.000112717,0.009630163,0.00002973969,0.00002081915,0.00004634467,0.0004683773,0.00002421789,0.001224477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01361109,"threshold_uncertainty_score":0.02706373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01805866738128525,"score_gpt":0.2060554513238867,"score_spread":0.1879967839426014,"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."}}