{"id":"W4399050454","doi":"10.1177/03019233241250132","title":"DT-MNLR: a novel hybrid machine learning framework for precise coke strength and reactivity prediction","year":2024,"lang":"en","type":"article","venue":"Ironmaking & Steelmaking Processes Products and Applications","topic":"Coal and Coke Industries Research","field":"Energy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"ShanXi Science and Technology Department","keywords":"Coke; Mechanical strength; Reactivity (psychology); Materials science; Metallurgy; Composite material; Computer science","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":[0.0003205737,0.0002604541,0.0002403866,0.0001440243,0.0007027154,0.0004532281,0.0001650089,0.0001208362,0.00001869638],"category_scores_gemma":[0.0006575432,0.0002357763,0.00003494219,0.0006183768,0.0001534929,0.0003265664,0.0001714729,0.0006158709,0.000004900251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000595632,"about_ca_system_score_gemma":0.0001928189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001032249,"about_ca_topic_score_gemma":0.00006979555,"domain_scores_codex":[0.998091,0.00002723482,0.0002954446,0.000907653,0.0002676895,0.0004110097],"domain_scores_gemma":[0.9986799,0.0006081726,0.0001092563,0.0003082163,0.0001924332,0.0001019583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008039799,0.000212249,0.0006501777,0.002222476,0.00009037906,0.000003294834,0.0008837729,0.0004109265,0.0045251,0.1947381,0.0001347643,0.7960483],"study_design_scores_gemma":[0.0002211575,0.0001179279,0.0004056832,0.0004515319,0.00008914267,0.00007599616,0.0002382888,0.004735863,0.004839631,0.006294074,0.9822338,0.0002968948],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3630686,0.0688033,0.5168667,0.0142713,0.001127925,0.01017938,0.002090456,0.004343092,0.01924934],"genre_scores_gemma":[0.9898579,0.0007484705,0.00321124,0.00002891333,0.0008618414,0.001228254,0.0001164705,0.00006621888,0.003880717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9820991,"threshold_uncertainty_score":0.9614677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03489076031896634,"score_gpt":0.2963624560295296,"score_spread":0.2614716957105633,"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."}}