{"id":"W4407757001","doi":"10.1002/cjce.25635","title":"Data‐driven deep learning prediction of full molecular weight distribution in polymerization processes","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Polymerization; Molar mass distribution; Distribution (mathematics); Deep learning; Artificial intelligence; Computer science; Materials science; Mathematics; Polymer; Composite material","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006306145,0.0005024984,0.0004231637,0.0004148172,0.0001793954,0.0005229376,0.0007115408,0.0007058636,0.0008760982],"category_scores_gemma":[0.001635256,0.0003275652,0.0003845321,0.0003117298,0.0003703374,0.0006531212,0.000368986,0.0010139,0.0001905644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047055,"about_ca_system_score_gemma":0.0009985964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008814729,"about_ca_topic_score_gemma":0.006770931,"domain_scores_codex":[0.9999208,0.00001579264,0.000004191179,0.00002275705,0.00001794551,0.00001846611],"domain_scores_gemma":[0.9993784,0.0003889036,0.00005746608,0.0000304224,0.0001117175,0.00003299027],"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":[0.00001967244,0.00003817549,0.0006436057,0.00001561427,0.000006941124,0.000009759946,0.000005131309,0.9924453,0.0007651853,0.0004546456,0.0001247485,0.00547121],"study_design_scores_gemma":[6.784473e-7,0.000001511224,0.00002906526,3.275867e-7,2.968432e-7,3.418515e-7,2.699419e-7,0.9996986,0.0001858973,0.00007240793,0.00001028128,3.187403e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7086545,0.0004329268,0.2862697,0.000366445,0.0000461874,0.00004509682,0.0003742093,0.00074056,0.003070307],"genre_scores_gemma":[0.985456,0.00008605961,0.01305146,0.00004490116,0.000006726063,0.00004000617,0.0002446201,0.00002322286,0.001046965],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008814729,"threshold_uncertainty_score":0.01752681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005308070906853448,"score_gpt":0.2065568479914966,"score_spread":0.2012487770846431,"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."}}