{"id":"W4394015350","doi":"10.1016/j.infsof.2024.107468","title":"Effective test generation using pre-trained Large Language Models and mutation testing","year":2024,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Test (biology); Mutation; Computer science; Natural language processing; Genetics; Biology; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003156947,0.000124388,0.0001131727,0.0004882875,0.0001850509,0.0003160165,0.0001331004,0.0001542559,7.683826e-7],"category_scores_gemma":[0.001276847,0.0001164734,0.00001425631,0.0005956185,0.00005256283,0.00173682,0.0001542251,0.0001613955,0.000003502106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004281879,"about_ca_system_score_gemma":0.000044141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003839129,"about_ca_topic_score_gemma":0.000003532882,"domain_scores_codex":[0.9992799,0.00001894615,0.0002233511,0.0001913958,0.0001083097,0.00017811],"domain_scores_gemma":[0.9992214,0.0003773888,0.0000708986,0.0001859578,0.0001093665,0.00003500283],"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":[0.000001362817,0.00001321039,0.002531554,0.0001250111,0.00001047724,0.00001567116,0.004026331,0.0002925196,0.0006906574,0.01359391,0.0002477223,0.9784516],"study_design_scores_gemma":[0.0001460956,0.0001014752,0.0007259908,0.00009629407,0.00000750205,0.0003075525,0.00003666068,0.9643289,0.0007541211,0.03326168,0.00009088668,0.0001428841],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1505017,0.0004333632,0.835888,0.0001577461,0.00007520317,0.0002267382,0.000007201062,0.01266615,0.00004392647],"genre_scores_gemma":[0.7107661,0.000006381202,0.289024,0.0001269255,0.0000200501,0.0000343907,0.00001165395,0.000005605948,0.0000049166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9783087,"threshold_uncertainty_score":0.4749646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01684748034253352,"score_gpt":0.2775876674362418,"score_spread":0.2607401870937083,"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."}}