{"id":"W4416046127","doi":"10.1016/j.mineng.2025.109910","title":"Predicting the Semi-Autogenous Grinding (SAG) power index based on rock geochemical composition using machine learning algorithms","year":2025,"lang":"en","type":"article","venue":"Minerals Engineering","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hudbay Minerals (Canada)","funders":"","keywords":"Gradient boosting; Random forest; Boosting (machine learning); Ensemble learning; Predictive modelling; Mill; Grind; Pulverizer","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003290511,0.0004391442,0.0003516423,0.0003844642,0.000366544,0.0001777284,0.0002812202,0.0001958929,0.00001799273],"category_scores_gemma":[0.0001072268,0.0003906848,0.0001183204,0.0007701973,0.00001681184,0.000157511,0.00007482109,0.0009804529,0.000004706036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002534735,"about_ca_system_score_gemma":0.00003016402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006728135,"about_ca_topic_score_gemma":0.000003668197,"domain_scores_codex":[0.9981898,0.00003614007,0.0004495358,0.0003638596,0.0003119285,0.0006487382],"domain_scores_gemma":[0.9992635,0.0002264656,0.00006378027,0.0002838769,0.00005924806,0.0001030788],"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":[0.000008471688,0.00001705008,0.003734292,0.0001445993,0.00004746053,0.00001359898,0.0001208292,0.7936986,0.2019444,0.00002706624,0.00005603179,0.0001875852],"study_design_scores_gemma":[0.0004339893,0.00002584872,0.0004610151,0.0006166795,0.00004199582,0.00002719593,0.00003224101,0.9698572,0.02709983,0.000005340494,0.001024036,0.0003746847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8599781,0.0006898376,0.1358129,0.00008775459,0.0006773333,0.0002097439,0.00001172402,0.00101469,0.001517867],"genre_scores_gemma":[0.9978919,0.00001036795,0.001330578,0.00009765353,0.0002544659,0.00002835099,0.00004626458,0.00009212569,0.0002483037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1761585,"threshold_uncertainty_score":0.9998545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007738186962980718,"score_gpt":0.2146222074826554,"score_spread":0.2068840205196746,"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."}}