{"id":"W4308498506","doi":"10.1016/j.conbuildmat.2022.129534","title":"Compressive strength prediction of one-part alkali activated material enabled by interpretable machine learning","year":2022,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Concrete and Cement Materials Research","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"National Natural Science Foundation of China","keywords":"Compressive strength; Durability; Computer science; Machine learning; Process engineering; Geopolymer; Artificial intelligence; Materials science; Composite material; Engineering; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001682231,0.0004479102,0.0003162448,0.0004585865,0.0001264608,0.0003249922,0.000486876,0.0005321271,0.001047526],"category_scores_gemma":[0.0003912902,0.0002047984,0.0003218336,0.0003120019,0.0002379464,0.0004631911,0.0002131912,0.0003717116,0.0002322167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002741892,"about_ca_system_score_gemma":0.0003062194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002649588,"about_ca_topic_score_gemma":0.004272273,"domain_scores_codex":[0.9999332,0.000006253814,0.000003017777,0.00002227332,0.00002589048,0.000009432547],"domain_scores_gemma":[0.9998088,0.00007208807,0.00002932575,0.00001878918,0.00005951518,0.00001151855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008308294,0.0002416867,0.007925422,0.0002389205,0.00006195495,0.0002717556,0.00006157844,0.6275765,0.2460543,0.001185511,0.000849996,0.1147016],"study_design_scores_gemma":[0.000003175577,0.0000324294,0.00153428,0.000001628979,0.00000658293,0.00001119647,0.000005336371,0.979912,0.01821963,0.0001640452,0.0001038971,0.000005823416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9017,0.000340128,0.09403918,0.00009408189,0.00004255966,0.00002337978,0.0002958551,0.0008376004,0.002627289],"genre_scores_gemma":[0.9930992,0.00006425721,0.006111378,0.00001017908,0.000004989823,0.000007672716,0.000114091,0.00001253796,0.000575765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002649588,"threshold_uncertainty_score":0.005268395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01044498149682488,"score_gpt":0.2146196378997796,"score_spread":0.2041746564029548,"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."}}