{"id":"W4416617174","doi":"10.48550/arxiv.2510.20052","title":"Endogenous Aggregation of Multiple Data Envelopment Analysis Scores for Large Data Sets","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Efficiency Analysis Using DEA","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Data envelopment analysis; Benchmarking; Aggregate (composite); Measure (data warehouse); Linear programming; Regularization (linguistics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01013719,0.0008750465,0.002278987,0.004181206,0.001057093,0.0003792307,0.01872659,0.0006532805,0.0004289682],"category_scores_gemma":[0.007799999,0.0009428241,0.001052027,0.01174603,0.0005155068,0.001437652,0.0214851,0.0006215291,0.00008939616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004044592,"about_ca_system_score_gemma":0.002115853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001505403,"about_ca_topic_score_gemma":0.005594857,"domain_scores_codex":[0.9879516,0.001061513,0.002252833,0.006556494,0.001124964,0.001052605],"domain_scores_gemma":[0.9712647,0.005818577,0.003158302,0.01754559,0.001871601,0.0003412206],"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":[0.0006751455,0.001991529,0.1281942,0.0003575281,0.01021119,0.0001320805,0.001208657,0.8363643,0.0001607452,0.005840346,0.001813237,0.01305102],"study_design_scores_gemma":[0.001483221,0.00006143968,0.003050517,0.0002327194,0.0108981,0.000001462634,0.001043938,0.9729827,0.0004685424,0.003384487,0.005587603,0.0008052344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1403594,0.0007067728,0.8303296,0.0001050966,0.0008468942,0.001514171,0.02531807,0.00007143991,0.0007486175],"genre_scores_gemma":[0.9802045,0.001327849,0.006448661,0.00007322339,0.00005700637,0.000002262298,0.009394327,0.00002527619,0.002466942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8398451,"threshold_uncertainty_score":0.9993022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.343604074799454,"score_gpt":0.3102741376699731,"score_spread":0.03332993712948085,"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."}}