{"id":"W4367680900","doi":"10.1177/03611981231161051","title":"Novel Soft-Computing Approach to Better Predict Flexible Pavement Roughness","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Random forest; Feature selection; Computer science; Support vector machine; Lasso (programming language); International Roughness Index; Multilayer perceptron; Linear regression; Artificial neural network; Feature (linguistics); Decision tree; Regression; Machine learning; Data mining; Engineering; Mathematics; Statistics; Surface finish","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":[0.003612906,0.0002709136,0.0003994131,0.001284589,0.0005195456,0.0001591457,0.00104204,0.0001638612,0.00004236469],"category_scores_gemma":[0.00007607834,0.0002106287,0.0002858775,0.003412744,0.0001868413,0.0004449867,0.00001290132,0.001957339,0.00004270447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002991828,"about_ca_system_score_gemma":0.0002039888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001207963,"about_ca_topic_score_gemma":0.001205277,"domain_scores_codex":[0.9939292,0.0002253549,0.001126076,0.000361214,0.003104637,0.001253511],"domain_scores_gemma":[0.9970554,0.0003772062,0.0001387206,0.0004294346,0.001611406,0.0003877946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0006359723,0.0002545327,0.1278523,0.001345563,0.0005160484,0.0001289828,0.01309283,0.6951485,0.06696678,0.002007908,0.04618775,0.04586287],"study_design_scores_gemma":[0.001524759,0.000305084,0.951035,0.0006206367,0.00004222385,0.000001284752,0.003615009,0.0085535,0.01099859,0.001119606,0.02181198,0.0003723541],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9135574,0.0000514572,0.08242781,0.0008300539,0.001500894,0.0009066818,0.00005228988,0.000182109,0.0004913557],"genre_scores_gemma":[0.990369,0.0001532554,0.00802335,0.00005292867,0.0007057823,0.00008048634,0.0000280942,0.00009732917,0.0004897758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8231826,"threshold_uncertainty_score":0.8589188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06660972202971738,"score_gpt":0.3405934917346597,"score_spread":0.2739837697049423,"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."}}