{"id":"W4391462747","doi":"10.1109/ms.2024.3418570","title":"Generative AI to Generate Test Data Generators","year":2024,"lang":"en","type":"preprint","venue":"IEEE Software","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Generative grammar; Test (biology); Computer science; Artificial intelligence; Test data; Natural language processing; Programming language","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":[0.00450908,0.0009477274,0.000706382,0.001920807,0.0005450813,0.001588282,0.002418801,0.001116815,0.004005122],"category_scores_gemma":[0.02456982,0.0006420363,0.001436691,0.001320449,0.002615177,0.001887813,0.002183272,0.002474938,0.001150868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033346,"about_ca_system_score_gemma":0.001012799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001259021,"about_ca_topic_score_gemma":0.002384437,"domain_scores_codex":[0.9961234,0.00204696,0.0001770249,0.0005155173,0.0009653266,0.0001718401],"domain_scores_gemma":[0.9796188,0.01471737,0.000414883,0.003780907,0.00125826,0.0002096586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001930204,0.0002617545,0.00403321,0.0004241799,0.0001690585,0.0004171345,0.001492406,0.2378835,0.01769236,0.4595483,0.007741562,0.2701435],"study_design_scores_gemma":[0.00005947733,0.00007572523,0.000293984,0.00004293595,0.00003307348,0.0001964648,0.00007705436,0.7836094,0.009780834,0.1991,0.006700213,0.00003088275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004023355,0.0000429006,0.992638,0.0001644012,0.00002257779,0.00008417661,0.0000814334,0.001053446,0.001889694],"genre_scores_gemma":[0.2140183,0.0001269714,0.7792801,0.000388911,0.00005855129,0.0007108093,0.0007246843,0.0009261003,0.003765614],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00450908,"threshold_uncertainty_score":0.02384657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06607790163968237,"score_gpt":0.3343913292862057,"score_spread":0.2683134276465233,"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."}}