{"id":"W4391986589","doi":"10.1145/3643991.3645074","title":"Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Programming language; Code generation; Code (set theory); Code review; Software engineering; Static program analysis; Software; Software development; Operating system","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":[0.02108944,0.0007569448,0.0005448987,0.001503856,0.0008829634,0.002151219,0.001459982,0.001400661,0.001866865],"category_scores_gemma":[0.160248,0.0005000824,0.0004785924,0.001228456,0.001157194,0.004109416,0.002646843,0.002121387,0.00119639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001469114,"about_ca_system_score_gemma":0.001989878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003269503,"about_ca_topic_score_gemma":0.004892909,"domain_scores_codex":[0.9802092,0.01573815,0.0007044063,0.001426559,0.001594047,0.0003276728],"domain_scores_gemma":[0.7504737,0.2201537,0.007016737,0.01371527,0.00510544,0.003535111],"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":[0.005211847,0.00573911,0.2983019,0.004602653,0.0003935,0.001218388,0.07130799,0.03249638,0.01412791,0.00775176,0.0335069,0.5253416],"study_design_scores_gemma":[0.002413671,0.008988094,0.2801032,0.00199245,0.0007528836,0.001907028,0.03403548,0.5187798,0.0208386,0.02127518,0.1083985,0.0005151295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9715672,0.0006154574,0.01847304,0.0009656067,0.00005389868,0.0004542143,0.001198834,0.00296359,0.003708206],"genre_scores_gemma":[0.9642388,0.0003239634,0.02776914,0.0002957328,0.00003682643,0.0009082719,0.004706729,0.0005773182,0.001143418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02108944,"threshold_uncertainty_score":0.1115329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1782814047691914,"score_gpt":0.4102592759568877,"score_spread":0.2319778711876963,"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."}}