{"id":"W4382862920","doi":"10.1016/j.cma.2023.116182","title":"Optimal design of validation experiments for the prediction of quantities of interest","year":2023,"lang":"en","type":"article","venue":"Computer Methods in Applied Mechanics and Engineering","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computation; Computer science; Model selection; Experimental data; Cross-validation; Design of experiments; Model validation; Algorithm; Mathematical optimization; Mathematics; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.009245732,0.001195645,0.0015541,0.000962838,0.000464809,0.001078106,0.001187161,0.001623524,0.001763944],"category_scores_gemma":[0.01939739,0.0009585575,0.0008123561,0.0003006487,0.001788559,0.001523763,0.001353861,0.001275656,0.0003058921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070083,"about_ca_system_score_gemma":0.002722142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009875163,"about_ca_topic_score_gemma":0.0008969465,"domain_scores_codex":[0.99604,0.002400523,0.0001463627,0.0006419749,0.0004986249,0.0002725179],"domain_scores_gemma":[0.9876881,0.008842225,0.00149235,0.0007048846,0.001035297,0.00023708],"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":[0.003350792,0.0008782297,0.002901344,0.0006970107,0.0001713242,0.00008794305,0.0001489068,0.7703506,0.06423245,0.03168068,0.001025149,0.1244755],"study_design_scores_gemma":[0.0002209383,0.0005967244,0.00121645,0.00004689518,0.00004247193,0.00002114112,0.00002295644,0.9611263,0.02429772,0.0114784,0.0009015448,0.00002845161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03387529,0.00026482,0.9639967,0.0001814315,0.00003923904,0.0003435659,0.00007460293,0.00025065,0.0009736787],"genre_scores_gemma":[0.6921678,0.0002146364,0.3052002,0.0001372238,0.000031802,0.001199959,0.0002219288,0.00007981859,0.0007466636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009245732,"threshold_uncertainty_score":0.04889673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3323481384152943,"score_gpt":0.4024437203644405,"score_spread":0.07009558194914628,"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."}}