{"id":"W4388902383","doi":"10.1016/j.autcon.2023.105164","title":"Reinforcement bond performance in 3D concrete printing: Explainable ensemble learning augmented by deep generative adversarial networks","year":2023,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Innovations in Concrete and Construction Materials","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning","keywords":"Computer science; Generative grammar; Reinforcement learning; Process (computing); Reinforcement; Artificial intelligence; 3D printing; Generative adversarial network; Machine learning; Adversarial system; Deep learning; Engineering; Structural engineering; Mechanical 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":[],"consensus_categories":[],"category_scores_codex":[0.0004886104,0.0001800011,0.0002105606,0.000463844,0.000167768,0.00008311955,0.00008038584,0.000158315,0.0001244104],"category_scores_gemma":[0.00005434375,0.0002215374,0.00002526972,0.001108653,0.00006153277,0.0005663247,0.00003441011,0.000251903,0.00004580919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002850434,"about_ca_system_score_gemma":0.00003345691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002580976,"about_ca_topic_score_gemma":0.000006810903,"domain_scores_codex":[0.9985197,0.00006724473,0.0006624855,0.0002265494,0.0001832455,0.0003408411],"domain_scores_gemma":[0.9995522,0.00005625104,0.0001393318,0.0001403619,0.00008421497,0.00002767927],"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":[0.00002550318,0.000001250178,0.007696009,0.00006214164,0.00002664708,0.000002974289,0.0005043193,0.941775,0.01974265,0.002575181,0.0004524628,0.02713588],"study_design_scores_gemma":[0.0009459586,0.00002825001,0.001567549,0.00007039032,0.00000616128,0.00001541735,0.0008455069,0.9743832,0.01955529,0.00006183622,0.002286776,0.0002336093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460259,0.00002348772,0.04717328,0.00003438162,0.001770912,0.0003608883,0.000002081929,0.0006726779,0.003936415],"genre_scores_gemma":[0.9953855,0.0001356655,0.003808326,0.00002119753,0.0001311099,0.0001596029,0.0002058892,0.00002523101,0.0001274961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0493596,"threshold_uncertainty_score":0.9034031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006778418230806195,"score_gpt":0.206862412205277,"score_spread":0.2000839939744709,"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."}}