{"id":"W4313119435","doi":"10.1145/3568364.3568380","title":"Identifying Candidate Classes for Unit Testing Using Deep Learning Classifiers: An Empirical Validation","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Unit testing; Empirical research; Unit (ring theory); Deep learning; Statistics; Mathematics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001048953,0.0001460745,0.0001532902,0.0002340838,0.001364743,0.0004548159,0.0006648544,0.00004208944,0.00001576175],"category_scores_gemma":[0.0008115569,0.0001547685,0.00005047549,0.0008089479,0.0000260231,0.0007076923,0.0004879047,0.0002899068,0.000001653969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001399024,"about_ca_system_score_gemma":0.0001302911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002693063,"about_ca_topic_score_gemma":0.000008601743,"domain_scores_codex":[0.9983019,0.0002540521,0.000272168,0.0004857229,0.0003269881,0.0003592249],"domain_scores_gemma":[0.9983185,0.0008908355,0.0001724364,0.0003667771,0.0001579713,0.00009345965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004115907,0.0003560027,0.5169733,0.0001452647,0.00006804214,0.0000706817,0.005864276,0.06856468,0.008419808,0.006640343,0.003759088,0.3890973],"study_design_scores_gemma":[0.0001687816,0.0002300102,0.001265349,0.0000189861,0.0000125102,0.0001047674,0.0001926377,0.9782168,0.0009241902,0.01787315,0.0007398264,0.0002530139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1217745,0.00002125632,0.869988,0.00008728693,0.0001947392,0.0001663583,0.000001065689,0.007526516,0.0002403401],"genre_scores_gemma":[0.4986979,3.259897e-7,0.5009835,0.000139042,0.00004583833,0.00004285165,0.0000115657,0.00001553301,0.00006336384],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9096521,"threshold_uncertainty_score":0.9999353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2139541627210256,"score_gpt":0.3930138495221044,"score_spread":0.1790596868010788,"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."}}