{"id":"W4321768195","doi":"10.1016/j.engstruct.2023.115771","title":"Predicting the drift capacity of precast concrete columns using explainable machine learning approach","year":2023,"lang":"en","type":"article","venue":"Engineering Structures","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Precast concrete; Structural engineering; Computer science; Engineering; Civil 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":[0.000259727,0.0002812968,0.0002995658,0.0001708476,0.0002055209,0.00005375739,0.0002792694,0.000124082,0.00001115322],"category_scores_gemma":[0.0001466052,0.0002321119,0.00009451407,0.0005368816,0.00005774383,0.00014207,0.00008469562,0.0006162822,0.000001410212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007517038,"about_ca_system_score_gemma":0.00001527225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001340314,"about_ca_topic_score_gemma":0.000001019394,"domain_scores_codex":[0.9986352,0.00002646427,0.0003166368,0.0002104414,0.0002574322,0.0005537951],"domain_scores_gemma":[0.9994382,0.0001042212,0.00006866609,0.0002720233,0.00005090634,0.00006603303],"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":[0.000003389267,4.245237e-7,0.001643146,0.0002563316,0.00007442853,0.000003770601,0.001525779,0.9607815,0.03498115,0.0004861822,0.00007317098,0.0001707151],"study_design_scores_gemma":[0.0002015115,0.00001918111,0.004813481,0.0000714795,0.00003244857,0.00003875248,0.0004162325,0.9668111,0.02575598,0.00007483902,0.001504421,0.0002605293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770463,0.0002794983,0.01983268,0.000005528653,0.001137196,0.0002358817,0.0000260844,0.0009298269,0.0005070676],"genre_scores_gemma":[0.9912889,0.00002577196,0.00808105,0.000004402126,0.000427856,0.00002024609,0.00001846555,0.00008662306,0.00004670894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01424264,"threshold_uncertainty_score":0.9465247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177939715975154,"score_gpt":0.1955428345832722,"score_spread":0.1837634374235207,"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."}}