{"id":"W7125607430","doi":"10.1109/cascon66301.2025.00036","title":"Generating Data Engineering Code Using Llms","year":2025,"lang":"","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Ambiguity; Benchmark (surveying); Correctness; Code (set theory); Raw data; Iterative refinement; Data modeling; Data management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002315832,0.001609857,0.0005049266,0.001450424,0.0005455264,0.001481531,0.002150013,0.0009856231,0.003782828],"category_scores_gemma":[0.01578445,0.0006722427,0.001258956,0.001576592,0.001078784,0.002068162,0.002348454,0.001664634,0.003588293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009183717,"about_ca_system_score_gemma":0.002111259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002976493,"about_ca_topic_score_gemma":0.00447936,"domain_scores_codex":[0.9971638,0.0005530695,0.0002812706,0.0007514844,0.00103703,0.0002132972],"domain_scores_gemma":[0.9910403,0.003184694,0.0004692646,0.00346886,0.001574295,0.0002625232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002058895,0.001152182,0.03874732,0.003458784,0.0003490461,0.001011734,0.001748112,0.08690543,0.06239526,0.01492975,0.1594404,0.627803],"study_design_scores_gemma":[0.0006414351,0.001215759,0.01270662,0.0003023543,0.0001313597,0.0007888627,0.0008022666,0.6339656,0.1972287,0.02304441,0.1290015,0.0001711669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.3105971,0.001577635,0.2334351,0.001041443,0.000519793,0.001215313,0.01710599,0.4184818,0.01602584],"genre_scores_gemma":[0.4272461,0.0006069679,0.4762157,0.0008482352,0.00006823621,0.0009519926,0.06110878,0.02609018,0.006863802],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003782828,"threshold_uncertainty_score":0.01265484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3205514175690622,"score_gpt":0.4424591552411957,"score_spread":0.1219077376721334,"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."}}