{"id":"W4408954605","doi":"10.1016/j.mtcomm.2025.112326","title":"Machine learning prediction of drying shrinkage for alkali-activated materials and multi-objective optimization","year":2025,"lang":"en","type":"article","venue":"Materials Today Communications","topic":"Concrete and Cement Materials Research","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of Guelph","funders":"Department of Education of Hebei Province; Hebei University of Technology; Hubei University of Technology; National Natural Science Foundation of China","keywords":"Shrinkage; Materials science; Alkali metal; Composite material; Organic chemistry","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":[0.0005209629,0.0001502623,0.0002986076,0.000189928,0.0002414162,0.0001171472,0.000274834,0.00009978782,0.000188997],"category_scores_gemma":[0.0001270258,0.0001597351,0.0000256521,0.0001736395,0.0000738601,0.0001782305,0.0002370717,0.00007450515,0.000001974106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005586974,"about_ca_system_score_gemma":0.00002255303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001569918,"about_ca_topic_score_gemma":0.00001090839,"domain_scores_codex":[0.9989029,0.0002015723,0.0004699226,0.0001557213,0.00008080524,0.000189129],"domain_scores_gemma":[0.9990726,0.0001676158,0.00009198613,0.0005070621,0.0001301824,0.00003052766],"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":[0.00004646389,0.00002338895,0.00008585957,0.0002661292,0.0000887102,8.15606e-8,0.0002985006,0.005137101,0.9929761,0.000580793,0.00003236473,0.000464552],"study_design_scores_gemma":[0.0007703832,0.00004199571,0.0005271807,0.0001401175,0.00004527443,7.541951e-7,0.0001472753,0.03916901,0.9579623,0.00007654222,0.001002982,0.0001161576],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569334,0.0007615299,0.03802956,0.0001770602,0.0004820494,0.001338254,0.00101408,0.00038171,0.0008823499],"genre_scores_gemma":[0.9878184,0.001777933,0.008950992,0.00001082198,0.00002335037,0.0003298612,0.0009062275,0.00003193862,0.0001504869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03501373,"threshold_uncertainty_score":0.6513809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02776537376663321,"score_gpt":0.2853107534934148,"score_spread":0.2575453797267815,"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."}}