{"id":"W4391713679","doi":"10.1016/j.conbuildmat.2024.135331","title":"Machine learning for predicting concrete carbonation depth: A comparative analysis and a novel feature selection","year":2024,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":53,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Carbonation; Feature selection; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Machine learning; Materials science; Computer science; Composite material","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":[0.00015274,0.0001304662,0.0002149637,0.000222914,0.0001428697,0.0002325965,0.00001915899,0.00008299698,0.000007554764],"category_scores_gemma":[0.00002412766,0.0001212253,0.00003228122,0.0002339091,0.00003885094,0.0001588717,0.00001232927,0.0001087698,1.591731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004269151,"about_ca_system_score_gemma":0.000007409067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002482804,"about_ca_topic_score_gemma":0.000008919456,"domain_scores_codex":[0.9994488,0.00001549883,0.0001509065,0.0001876762,0.0000569878,0.0001400979],"domain_scores_gemma":[0.9998004,0.00005644227,0.0000345608,0.00003097198,0.00004460447,0.00003303673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001767555,2.992857e-7,0.004108925,0.0001796346,0.0002996596,3.858283e-7,0.0003273058,0.002440589,0.9852253,0.002782492,0.00001329644,0.004604484],"study_design_scores_gemma":[0.0004514462,0.00004123241,0.004427753,0.0001759159,0.0005291809,0.0001306579,0.0003042207,0.3116564,0.6777542,0.0002890551,0.003968051,0.0002718375],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8632997,0.0003896609,0.1346929,0.00001957913,0.001018217,0.000152758,0.00002970283,0.0002979844,0.00009946959],"genre_scores_gemma":[0.98361,0.00006997561,0.01589684,0.000004451652,0.0003286964,0.00002533966,0.0000313575,0.00001341821,0.00001992777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3092158,"threshold_uncertainty_score":0.4943424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009793378918579333,"score_gpt":0.2469637145080101,"score_spread":0.2371703355894307,"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."}}