{"id":"W4323073170","doi":"10.1016/j.icheatmasstransfer.2023.106684","title":"Employing ensemble learning techniques for modeling nanofluids' specific heat capacity","year":2023,"lang":"en","type":"article","venue":"International Communications in Heat and Mass Transfer","topic":"Nanofluid Flow and Heat Transfer","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Nanofluid; Artificial neural network; Heat capacity; Computer science; Multilayer perceptron; Boosting (machine learning); Materials science; Random forest; Leverage (statistics); Gradient boosting; Perceptron; Machine learning; Heat transfer; Artificial intelligence; Thermodynamics","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":[0.0003256397,0.0001659952,0.0001870391,0.0003609003,0.0001948485,0.00006624133,0.0004002966,0.0001200786,0.00001802435],"category_scores_gemma":[0.00001156755,0.0001849152,0.00008345324,0.0002419192,0.00005455637,0.0002250007,0.00003019587,0.0003307701,0.0000111895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009316757,"about_ca_system_score_gemma":0.00001165138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006620598,"about_ca_topic_score_gemma":0.00008965359,"domain_scores_codex":[0.9990054,0.00003779442,0.0003576766,0.000193851,0.0001461606,0.0002591688],"domain_scores_gemma":[0.9993305,0.0001883095,0.000001732606,0.0003361315,0.00009134132,0.00005203813],"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":[0.00007470734,0.00009207939,0.004130343,0.000198265,0.000142201,0.000004177693,0.002935536,0.05289012,0.8855231,0.04095471,0.0004120078,0.01264274],"study_design_scores_gemma":[0.0007824526,0.00005055185,0.0002850413,0.000222025,0.00001856369,0.000008264507,0.0002416087,0.8771651,0.04840404,0.003986494,0.068414,0.0004219004],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4537015,0.001874992,0.5355046,0.001442478,0.000397641,0.000630584,0.00006104328,0.00100785,0.00537933],"genre_scores_gemma":[0.9809719,0.01164554,0.006659177,0.00004044703,0.00007376076,0.0003541706,0.000122327,0.00004949672,0.00008312459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8371191,"threshold_uncertainty_score":0.7540624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06616799176624236,"score_gpt":0.2877108236065382,"score_spread":0.2215428318402959,"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."}}