{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01293088,0.001286846,0.001312458,0.003494067,0.0006626273,0.003190494,0.001358996,0.0008211382,0.001184079],"category_scores_gemma":[0.04220928,0.0005660548,0.001465961,0.005134676,0.001275635,0.002858279,0.002831877,0.002266176,0.0001950414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003114193,"about_ca_system_score_gemma":0.002881706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004811485,"about_ca_topic_score_gemma":0.004589274,"domain_scores_codex":[0.9928618,0.004231495,0.0004519575,0.0008108394,0.001369879,0.0002740195],"domain_scores_gemma":[0.9777909,0.01464218,0.003012607,0.002410473,0.001898877,0.0002449185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004212419,0.0001072708,0.009331023,0.0001487011,0.0001996772,0.00008924225,0.0002974625,0.7929851,0.001015916,0.1049755,0.0008738429,0.08993415],"study_design_scores_gemma":[0.000004694294,0.00003227497,0.001399883,0.00003062749,0.00001355075,0.0000123189,0.00007511115,0.9524733,0.0007402205,0.04439139,0.0008099806,0.00001663709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0205598,0.0001048815,0.9775934,0.0002249836,0.00001329484,0.0000651648,0.0001088379,0.0001012567,0.001228294],"genre_scores_gemma":[0.5880381,0.000180753,0.4103987,0.00007212774,0.00002904485,0.0003103529,0.0002995949,0.00007491484,0.0005963162],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01293088,"threshold_uncertainty_score":0.06838578,"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."}}