{"id":"W3092657053","doi":"10.1016/j.conbuildmat.2020.121117","title":"Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete","year":2020,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Innovative concrete reinforcement materials","field":"Engineering","cited_by":402,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"National Research Foundation of Korea","keywords":"Flexural strength; Compressive strength; Silica fume; Overfitting; Fiber-reinforced concrete; Materials science; Structural engineering; Random forest; Computer science; Fiber; Artificial neural network; Machine learning; Composite material; Engineering","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":[0.000144722,0.0001817745,0.000357084,0.00007465382,0.00008343626,0.00007857686,0.00005006314,0.0000908926,0.0002866059],"category_scores_gemma":[0.0001250411,0.0001807473,0.00002599305,0.00007582604,0.0001400379,0.0001581736,0.00003230488,0.0000587252,0.00000131698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158214,"about_ca_system_score_gemma":0.00001322391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005247602,"about_ca_topic_score_gemma":3.973692e-8,"domain_scores_codex":[0.9990955,0.00003786933,0.0004479986,0.0001673861,0.00009098726,0.0001602313],"domain_scores_gemma":[0.999498,0.00009570115,0.0001730278,0.00006504923,0.0001042345,0.00006406628],"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":[0.0001450675,1.580263e-7,0.0000737295,0.0004529815,0.0000496183,2.758262e-7,0.00007766885,0.004044001,0.991304,0.002310292,0.00005040632,0.00149175],"study_design_scores_gemma":[0.001446886,0.000149151,0.00004143964,0.00009653252,0.00003646297,0.000005736522,0.00005556725,0.0738609,0.9201169,0.000013956,0.004018508,0.0001579664],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865137,0.00008184771,0.01166403,0.00005350724,0.0004394244,0.0004476144,0.0004366661,0.0002208792,0.0001423775],"genre_scores_gemma":[0.9953974,0.00005344395,0.0041566,0.00004329796,0.0001318368,0.00002960693,0.0001436757,0.00002561728,0.00001850708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07118715,"threshold_uncertainty_score":0.7370663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244724235980938,"score_gpt":0.2253780462767145,"score_spread":0.2129308039169051,"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."}}