{"id":"W4407463908","doi":"10.1016/j.heliyon.2025.e42714","title":"Machine learning-based prediction of pervaporation permeation using physicochemical properties of permeant-membrane and process conditions","year":2025,"lang":"en","type":"article","venue":"Heliyon","topic":"Membrane Separation and Gas Transport","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Malawi University of Science and Technology; Khalifa University of Science, Technology and Research","keywords":"Pervaporation; Permeation; Process (computing); Chemistry; Membrane; Chromatography; Computer science; Biochemistry","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":[0.0008182684,0.0008365458,0.000726383,0.0007446411,0.0002804975,0.0009149143,0.0004398979,0.0008108059,0.001347739],"category_scores_gemma":[0.002651172,0.0003248673,0.0006681255,0.0005174971,0.0002076173,0.0006256332,0.0002788845,0.0009572492,0.0006276479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006003152,"about_ca_system_score_gemma":0.0006496004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005904782,"about_ca_topic_score_gemma":0.003893983,"domain_scores_codex":[0.9998634,0.00002806726,0.0000150413,0.00005136787,0.00002698909,0.00001525843],"domain_scores_gemma":[0.9985871,0.001005705,0.0001063948,0.00004401971,0.0002193379,0.00003734494],"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":[0.0006354899,0.0005124597,0.02478465,0.0002007609,0.0002631957,0.0001021152,0.00003095706,0.8272934,0.0122938,0.0003163214,0.004411576,0.1291553],"study_design_scores_gemma":[0.000006218708,0.00003025314,0.001470625,0.000004111468,0.0000118642,0.000009380374,0.000003621934,0.996742,0.00145887,0.0001514964,0.0001057463,0.000005905575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8431863,0.002773033,0.1442395,0.001297688,0.0004274445,0.00009262884,0.002507366,0.002923464,0.002552456],"genre_scores_gemma":[0.9786587,0.0004845697,0.01734058,0.00007597431,0.00006409318,0.0000483469,0.001695497,0.00005421515,0.001578154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005904782,"threshold_uncertainty_score":0.01174086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01717569799032195,"score_gpt":0.2400153794814094,"score_spread":0.2228396814910874,"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."}}