{"id":"W4414631567","doi":"10.1080/14680629.2025.2559824","title":"Developing interpretable machine learning models for predicting the compressive strength of roller-compacted concrete","year":2025,"lang":"en","type":"article","venue":"Road Materials and Pavement Design","topic":"Innovative concrete reinforcement materials","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Compressive strength; Compression (physics); Predictive modelling; Pattern recognition (psychology); Artificial neural network","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":[0.0008057678,0.0002341241,0.0004529329,0.0001005674,0.0001645905,0.0001257023,0.0001648474,0.00006857324,0.00006906948],"category_scores_gemma":[0.00005596951,0.0001780215,0.0000327806,0.0001234559,0.00004328902,0.000157633,0.00008720809,0.0000692122,8.864525e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000055701,"about_ca_system_score_gemma":0.0000383629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005639212,"about_ca_topic_score_gemma":5.120464e-7,"domain_scores_codex":[0.9986686,0.0001371682,0.0006203129,0.0001721867,0.0001140671,0.0002876914],"domain_scores_gemma":[0.9992658,0.000257805,0.0001792687,0.0001473023,0.0001271095,0.00002271603],"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":[0.0001472735,0.000001617013,0.00004992377,0.0007025383,0.0003820055,4.615231e-7,0.0006279906,0.04626042,0.9405128,0.0105634,0.000148304,0.00060322],"study_design_scores_gemma":[0.0007298737,0.00006752476,0.0000365511,0.0003704151,0.00004848276,4.643751e-7,0.0001148436,0.3009555,0.6965147,0.0004767122,0.000535946,0.0001490396],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4573065,0.0003650586,0.5396504,0.00004170365,0.0005171853,0.001299497,0.0001141558,0.0001404105,0.0005651151],"genre_scores_gemma":[0.994832,0.0001701959,0.004483899,0.00006417743,0.00004642634,0.0001622839,0.00007749256,0.00002717446,0.0001363279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5375255,"threshold_uncertainty_score":0.7259505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03374406444731867,"score_gpt":0.248121145799668,"score_spread":0.2143770813523493,"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."}}