{"id":"W4409567383","doi":"10.1680/jinam.24.00028","title":"Exploring pavement friction variability factors using ensemble trees and causal inference","year":2025,"lang":"en","type":"article","venue":"Infrastructure Asset Management","topic":"Asphalt Pavement Performance Evaluation","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Natural Science Foundation of China","keywords":"Causal inference; Inference; Ensemble learning; Econometrics; Computer science; Environmental science; Artificial intelligence; Mathematics","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":[0.0002901383,0.0002438869,0.0001827674,0.0002496473,0.0001408509,0.00008831763,0.0001207145,0.00005897321,0.00006484571],"category_scores_gemma":[0.00001751692,0.0002402082,0.00003030058,0.0003351001,0.0000243763,0.0005921978,0.0001352925,0.0001540135,0.000003028017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003907334,"about_ca_system_score_gemma":0.00001453539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002057505,"about_ca_topic_score_gemma":0.00001793333,"domain_scores_codex":[0.9987932,0.00003994865,0.0003294802,0.0002870706,0.000268207,0.0002820364],"domain_scores_gemma":[0.999513,0.0000497727,0.00005117554,0.0002987823,0.00003796718,0.00004934431],"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":[0.0000136077,0.00004103376,0.2201919,0.0008703621,0.000534073,0.000006279433,0.001085872,0.685484,0.01223944,0.008066759,0.0006407609,0.07082593],"study_design_scores_gemma":[0.0004934932,0.00003090819,0.7551261,0.0001159742,0.0001638556,6.820016e-7,0.0007197515,0.2295013,0.007632197,0.003329761,0.002551443,0.0003345095],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8315579,0.00002727433,0.1641232,0.00001629441,0.0008429537,0.0003938502,0.000005160062,0.0001993513,0.002834042],"genre_scores_gemma":[0.9953419,0.0001405996,0.004291876,0.00002888699,0.0000459724,0.0000644774,0.00002841283,0.00001672845,0.00004116105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5349342,"threshold_uncertainty_score":0.9795406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0428145560701504,"score_gpt":0.2747844752700224,"score_spread":0.231969919199872,"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."}}