{"id":"W4403536220","doi":"10.1145/3691620.3695527","title":"Test-Driven Development and LLM-based Code Generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Test (biology); Code generation; Test-driven development; Programming language; Code (set theory); Software engineering; Software development; Operating system; Software","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":[0.005964712,0.0007259491,0.0003246905,0.001142158,0.0003710995,0.001218554,0.002355548,0.001174897,0.002685712],"category_scores_gemma":[0.04253117,0.0005903696,0.0006618479,0.0006851684,0.00168787,0.001557068,0.002124324,0.001361544,0.0009649718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151529,"about_ca_system_score_gemma":0.001872056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673738,"about_ca_topic_score_gemma":0.001744572,"domain_scores_codex":[0.9911054,0.004740098,0.0004782219,0.0007437387,0.002616675,0.0003158395],"domain_scores_gemma":[0.9702809,0.01920196,0.001787379,0.005453854,0.002878804,0.0003971257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007202806,0.001146604,0.01213254,0.001367722,0.0001383195,0.001027775,0.002024284,0.1774229,0.1001594,0.05872488,0.009421371,0.6357141],"study_design_scores_gemma":[0.0002609845,0.001130894,0.002954453,0.0002804839,0.00006666669,0.001030552,0.0002476333,0.7881896,0.1460242,0.03009641,0.02960835,0.0001097445],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06004842,0.0001893288,0.9193825,0.000763145,0.0000650865,0.0006694912,0.0002531654,0.01206355,0.006565268],"genre_scores_gemma":[0.3035403,0.0001487969,0.6912471,0.0004156629,0.00001475435,0.0007711087,0.0006032151,0.001144681,0.002114379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005964712,"threshold_uncertainty_score":0.0315448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04352896262435825,"score_gpt":0.2753428871041018,"score_spread":0.2318139244797435,"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."}}