{"id":"W4323663983","doi":"10.3390/su15064824","title":"Machine Learning-Based Flexural Capacity Prediction of Corroded RC Beams with an Efficient and User-Friendly Tool","year":2023,"lang":"en","type":"article","venue":"Sustainability","topic":"Concrete Corrosion and Durability","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Qatar National Research Fund; Fonds National de la Recherche Luxembourg; Qatar Foundation","keywords":"Overfitting; Support vector machine; Boosting (machine learning); Gradient boosting; Mean squared error; Computer science; Hyperparameter optimization; Artificial intelligence; Machine learning; Mean absolute percentage error; Decision tree; Hyperparameter; Reinforcement learning; Random forest; Mathematics; Statistics; 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":[0.0007485412,0.0001947349,0.0002651846,0.0001028394,0.0001230141,0.00002635879,0.0001016702,0.00009292486,0.00004388861],"category_scores_gemma":[0.0006254649,0.0001684767,0.00005576517,0.0004879512,0.0002415766,0.0001099769,0.00004659533,0.0002715158,0.000001815545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003270748,"about_ca_system_score_gemma":0.0001160404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002228477,"about_ca_topic_score_gemma":0.00007934061,"domain_scores_codex":[0.9986114,0.0001408715,0.0003041798,0.0003547628,0.000262927,0.0003258852],"domain_scores_gemma":[0.9988471,0.0001142637,0.00004749162,0.0004644313,0.0003929176,0.0001338244],"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":[0.000448497,0.0001218456,0.3033611,0.001433792,0.00001453615,0.000008426377,0.001148211,0.688565,0.001824713,0.0003429983,0.0000852642,0.002645693],"study_design_scores_gemma":[0.000751084,0.0005422469,0.2587381,0.00001346763,0.00001955204,0.000002281929,0.0006560105,0.7367324,0.001716235,0.00011646,0.0005442949,0.0001679393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895537,0.00002327165,0.008731104,0.00008463081,0.0001100775,0.0005600597,0.00007941341,0.0008035543,0.00005415933],"genre_scores_gemma":[0.9995697,0.000002178746,0.0002248806,0.000007003505,0.00001599146,0.00003881828,0.00006510533,0.00002345902,0.000052934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04816736,"threshold_uncertainty_score":0.6870282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008379569594862604,"score_gpt":0.2127682754739187,"score_spread":0.2043887058790561,"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."}}