{"id":"W2322744709","doi":"10.1021/ie302408b","title":"Development of a Model Selection Criterion for Accurate Model Predictions at Desired Operating Conditions","year":2012,"lang":"en","type":"article","venue":"Industrial & Engineering Chemistry Research","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Honeywell (Canada); Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Variance (accounting); Model selection; Monte Carlo method; Computer science; Nonlinear system; Computation; Selection (genetic algorithm); Mean squared error; Estimation theory; Linear model; Mathematical optimization; Algorithm; Mathematics; Statistics; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000557554,0.0001952573,0.0002574244,0.0001429191,0.0004231264,0.00004478135,0.0002228082,0.0003605838,0.0002894645],"category_scores_gemma":[0.0007649481,0.0002161375,0.00009345769,0.0006002989,0.00005347346,0.0002005351,0.0001181282,0.0005518959,0.000003074957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007287134,"about_ca_system_score_gemma":0.0003773155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006360837,"about_ca_topic_score_gemma":6.629493e-7,"domain_scores_codex":[0.9981456,0.000008220666,0.0004644565,0.0002761642,0.0004266132,0.000678894],"domain_scores_gemma":[0.9989869,0.0002005473,0.00008414281,0.0002117537,0.0002952234,0.0002214231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003288407,0.00009676569,0.0001291727,0.0001681117,0.00009023282,1.267778e-7,0.0002402471,0.1286281,0.8699754,0.00002798174,0.0005649705,0.00004600419],"study_design_scores_gemma":[0.0003724663,0.000004770581,0.000003762113,0.00003725561,0.00003332067,0.000003796694,0.00009379965,0.4082582,0.5908945,0.000005980509,0.000178403,0.0001137921],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834213,0.00009068046,0.01465513,0.00003008388,0.00004060382,0.0001749637,0.0001472569,0.0001288298,0.001311162],"genre_scores_gemma":[0.9918182,0.000006821917,0.004561118,0.000002083231,0.0004563954,0.0003342463,0.000196719,0.00004125582,0.002583118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2796301,"threshold_uncertainty_score":0.8813833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2731259629743426,"score_gpt":0.4157107935098835,"score_spread":0.1425848305355409,"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."}}