{"id":"W2536298395","doi":"10.1109/ieem58616.2023.10406676","title":"A Statistical Method of Goodness on Quantitative Models of Efficiency and Effectiveness","year":2023,"lang":"en","type":"article","venue":"","topic":"Efficiency Analysis Using DEA","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Premise; Goodness of fit; Consistency (knowledge bases); Computer science; Econometrics; Efficient-market hypothesis; Statistical hypothesis testing; Argument (complex analysis); Statistical model; Statistical analysis; Artificial intelligence; Machine learning; Statistics; Economics; Mathematics","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":[0.009343847,0.0001260622,0.00058225,0.0007263928,0.00007184943,0.00003327155,0.0003960312,0.0000568805,0.00006254791],"category_scores_gemma":[0.006233647,0.0000829417,0.00009349027,0.003126011,0.0003436363,0.0001299599,0.0001354473,0.00008281024,0.00005201552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001292955,"about_ca_system_score_gemma":0.00006927287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001182588,"about_ca_topic_score_gemma":0.00001246465,"domain_scores_codex":[0.9960875,0.001095171,0.0006697994,0.0005261022,0.001417912,0.0002035428],"domain_scores_gemma":[0.975584,0.02322752,0.0002419474,0.0004242701,0.0004548343,0.00006745211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000143379,0.0001996677,0.001769865,0.00004002956,0.00003489153,0.000005771162,0.001138565,0.1528939,0.005152764,0.8298661,0.0001039556,0.008651152],"study_design_scores_gemma":[0.0003088464,0.0004466066,0.0236614,0.00004522984,0.00003281401,0.000001528974,0.001354502,0.7995079,0.009118957,0.1653983,0.000009698083,0.0001142519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3773117,0.00001948909,0.6201388,0.00004206161,0.00004855458,0.0001009458,0.00003047807,0.00001993163,0.002287994],"genre_scores_gemma":[0.9759479,0.00000405923,0.02390618,0.00001499808,0.000002876223,0.000005194262,0.000001774383,0.000007316058,0.0001097745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6644678,"threshold_uncertainty_score":0.7462708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1913106925975522,"score_gpt":0.4900336599307532,"score_spread":0.298722967333201,"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."}}