{"id":"W4412603719","doi":"10.1016/j.gsme.2026.03.001","title":"Artificial Neural Network Modeling of Rare Earth Element Solvent Extraction Based on Ph and Extractant Concentration","year":2025,"lang":"en","type":"preprint","venue":"Green and Smart Mining Engineering","topic":"Extraction and Separation Processes","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Rare earth; Extraction (chemistry); Rare-earth element; Solvent extraction; Artificial neural network; Solvent; Element (criminal law); Chemistry; Organic solvent; Computer science; Chromatography; Artificial intelligence; Chemical engineering; Mineralogy; Organic chemistry; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002477312,0.0004215289,0.0004662246,0.0002289535,0.0002394372,0.000506493,0.0005826512,0.0009017594,0.001279749],"category_scores_gemma":[0.0005712771,0.0003074252,0.0005037807,0.0003578642,0.0002690889,0.0005748081,0.0002193366,0.0004878885,0.000194888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005856783,"about_ca_system_score_gemma":0.0004595067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01352712,"about_ca_topic_score_gemma":0.008367497,"domain_scores_codex":[0.999922,0.00001767793,0.000004342696,0.00002297525,0.00002213891,0.00001088902],"domain_scores_gemma":[0.9998134,0.0001030127,0.000019057,0.000007097635,0.00005262539,0.000004793467],"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":[0.00003130354,0.00001524451,0.0003019885,0.00002225147,0.00001333431,0.00002102003,0.000009010905,0.9934584,0.001719478,0.0004351758,0.00009616539,0.003876587],"study_design_scores_gemma":[5.829863e-7,0.000002529765,0.00004431507,5.495878e-7,0.000001392038,0.000001228298,6.57181e-7,0.999622,0.0002494087,0.00005426863,0.00002228646,7.757943e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.522149,0.001462897,0.4571578,0.0005852508,0.0001939451,0.00006739205,0.0003425741,0.0005473825,0.01749375],"genre_scores_gemma":[0.9849879,0.0003575623,0.007342701,0.00003469603,0.00001596227,0.00004148707,0.00009943124,0.00002365382,0.00709657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01352712,"threshold_uncertainty_score":0.02689677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0244938928273053,"score_gpt":0.2490606964848236,"score_spread":0.2245668036575183,"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."}}