{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007905639,0.0008207479,0.0006746313,0.0005151604,0.0004308498,0.001460529,0.006891445,0.0005193544,0.00001335837],"category_scores_gemma":[0.001702279,0.000781355,0.0001727355,0.0008988958,0.00007543144,0.0002766009,0.02089871,0.001591902,0.0005279829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000230325,"about_ca_system_score_gemma":0.00107014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000236557,"about_ca_topic_score_gemma":0.0000412572,"domain_scores_codex":[0.9947925,0.000149842,0.0006526725,0.002923238,0.0007348969,0.0007469062],"domain_scores_gemma":[0.9919965,0.0005367051,0.0001942469,0.006402212,0.0004433633,0.0004269479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001949093,0.00007171521,0.0008144461,0.0001882346,0.00008398412,0.0002772715,0.0008101612,0.002214569,0.0001680627,0.0002626229,0.9587247,0.03638231],"study_design_scores_gemma":[0.0003844529,0.0005152943,0.0002815866,0.002819311,0.0002767965,0.0002474014,0.000005769979,0.3753757,0.0319814,0.5258946,0.05671274,0.005505013],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003939874,0.001790351,0.944635,0.003761155,0.006668181,0.0007034603,0.001069069,0.03734825,0.00008464838],"genre_scores_gemma":[0.03472124,0.00004938627,0.9539964,0.007593847,0.00217197,0.0003042894,0.0003213047,0.000158617,0.000682965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9020119,"threshold_uncertainty_score":0.999576,"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."}}