{"id":"W4410529857","doi":"10.1016/j.bej.2025.109800","title":"Structural design of cellulose derivative-modified chitosan adsorbents for arsenic removal: Machine learning modeling, Box-Behnken design, Optuna hyperparameter tuning, and molecular dynamics","year":2025,"lang":"en","type":"article","venue":"Biochemical Engineering Journal","topic":"Arsenic contamination and mitigation","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Universiti Sains Malaysia","keywords":"Box–Behnken design; Chitosan; Cellulose; Adsorption; Derivative (finance); Chemistry; Chromatography; Hyperparameter; Chemical engineering; Materials science; Organic chemistry; Mathematics; Response surface methodology; Engineering; Algorithm","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":[0.0002243072,0.0001690617,0.0001870273,0.00008233956,0.00007900823,0.00003298478,0.0001507127,0.0001018652,0.00001951082],"category_scores_gemma":[0.0002938589,0.0001640405,0.0000720449,0.0001289212,0.00005203727,0.00009613846,0.00008566883,0.0002678099,4.508061e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001339277,"about_ca_system_score_gemma":0.00002728237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009387245,"about_ca_topic_score_gemma":2.458052e-7,"domain_scores_codex":[0.9990302,0.00004631471,0.0003177109,0.0002101469,0.0001762109,0.0002193659],"domain_scores_gemma":[0.9995809,0.00009185011,0.0001085506,0.00009510454,0.00002034377,0.0001032826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003919091,0.00001077236,0.0001179636,0.0000166318,0.00002745209,0.000002835367,0.0001149301,0.3768655,0.6200556,0.000124551,0.00001183927,0.002612821],"study_design_scores_gemma":[0.000583076,0.00005110493,0.0001294879,0.00005420791,0.00003228918,0.00003631766,0.00001989055,0.8602003,0.1385245,0.000213382,0.00001789925,0.0001375391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4480276,0.0001298786,0.5515723,0.00004168897,0.00004822884,0.0001357786,0.000001608323,0.0000173803,0.00002554185],"genre_scores_gemma":[0.89145,0.00002333539,0.1083774,0.00002836683,0.00001336284,0.000007329413,0.00001208,0.00001775419,0.00007038433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4833349,"threshold_uncertainty_score":0.6689376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01287889549361212,"score_gpt":0.2260045972398174,"score_spread":0.2131257017462053,"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."}}