{"id":"W4414052478","doi":"10.1016/j.conbuildmat.2025.143369","title":"Hybrid generative adversarial network and machine learning approach for performance prediction of marshall stability and marshall flow of recycled asphalt shingle pavements","year":2025,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; McMaster University","funders":"","keywords":"Asphalt; Gradation; Stability (learning theory); Artificial neural network; Performance prediction; Generalization; Key (lock); Generative grammar","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":[0.0003295408,0.000127635,0.0002711167,0.00006140919,0.0001113106,0.00003452416,0.00003318128,0.0000650917,0.00001019316],"category_scores_gemma":[0.00003164298,0.000122987,0.00001819051,0.0000487687,0.0000945159,0.0001471082,0.00004527401,0.00006409024,9.928987e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002660876,"about_ca_system_score_gemma":0.00001059761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001363974,"about_ca_topic_score_gemma":7.158029e-7,"domain_scores_codex":[0.9992585,0.00003950771,0.0003179209,0.000178048,0.00005893955,0.0001470834],"domain_scores_gemma":[0.9997146,0.00003404791,0.00009657087,0.00006888382,0.00005931534,0.0000265718],"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":[0.0003680317,0.00001250561,0.03765686,0.001922837,0.0001754331,2.164816e-7,0.000274271,0.01026241,0.8965183,0.001337918,0.00004259633,0.0514286],"study_design_scores_gemma":[0.001387646,0.00009213742,0.004994672,0.0002367623,0.0000794334,0.00001257294,0.00011701,0.08356484,0.9081193,0.0009558194,0.0002996305,0.0001402309],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9274029,0.0002367696,0.07087012,0.000003801369,0.001030763,0.0002323345,0.00007847556,0.00004050197,0.0001043555],"genre_scores_gemma":[0.9575581,0.0003622574,0.04184443,0.000004454208,0.0001604365,0.00001984759,0.00003399757,0.00001011787,0.000006359619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07330244,"threshold_uncertainty_score":0.5015266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01162721071899831,"score_gpt":0.2056442364232142,"score_spread":0.1940170257042159,"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."}}