{"id":"W4224222480","doi":"10.3390/ma15082742","title":"Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns","year":2022,"lang":"en","type":"article","venue":"Materials","topic":"Structural Behavior of Reinforced Concrete","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Fibre-reinforced plastic; Gradient boosting; Support vector machine; Harmony search; Categorical variable; Boosting (machine learning); Computer science; Structural engineering; Artificial intelligence; Machine learning; Random forest; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000382012,0.0002112666,0.0003791392,0.00007787854,0.0002038647,0.00007197753,0.0004756627,0.00003839772,0.003767676],"category_scores_gemma":[0.00007309542,0.0001824375,0.00007766548,0.0001803364,0.00005775695,0.0001081272,0.0003089605,0.0002494953,0.00002329969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321332,"about_ca_system_score_gemma":0.00001878557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007926395,"about_ca_topic_score_gemma":0.00000132438,"domain_scores_codex":[0.9985808,0.0001002891,0.0004564428,0.0001716957,0.0003413718,0.0003494136],"domain_scores_gemma":[0.9993782,0.00007368283,0.0001003452,0.0003241913,0.00003973334,0.00008382001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006002957,6.365197e-8,0.00005193602,0.00003137083,0.00005042999,0.000006835493,0.0007951636,0.04897223,0.9493188,0.0001293459,0.0002936645,0.0002901025],"study_design_scores_gemma":[0.0005276373,0.0002717374,0.0002416878,0.00002254521,0.00005631448,0.00007930357,0.0002163939,0.03951338,0.950036,0.00001137542,0.008697686,0.0003259056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957587,0.00002394933,0.0006531262,0.00002989807,0.001549831,0.0005091577,0.0004977864,0.0002961397,0.0006814165],"genre_scores_gemma":[0.9980764,0.0000043641,0.000814941,0.00006555561,0.0001017692,0.0001554285,0.00006837621,0.00004658546,0.0006665504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009458855,"threshold_uncertainty_score":0.997143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110687427149752,"score_gpt":0.2086356979271309,"score_spread":0.1975288236556334,"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."}}