{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01089139,0.002051717,0.0009736588,0.002126192,0.0006240841,0.00143956,0.002245457,0.002260831,0.001136781],"category_scores_gemma":[0.0417713,0.0004835399,0.000990321,0.001086997,0.001043885,0.002217775,0.00161026,0.002408991,0.0006994042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001292913,"about_ca_system_score_gemma":0.001575427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004352107,"about_ca_topic_score_gemma":0.006324919,"domain_scores_codex":[0.9936051,0.002922935,0.0005709775,0.001293879,0.001149957,0.0004571112],"domain_scores_gemma":[0.9514645,0.03644149,0.00172865,0.00443384,0.005294177,0.0006372895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002599102,0.003260833,0.203456,0.0009897392,0.0006911763,0.0004388067,0.000693072,0.3593583,0.0134791,0.002403943,0.01266752,0.3999624],"study_design_scores_gemma":[0.00007608844,0.0004503792,0.009972617,0.0001529195,0.00007832345,0.0000857489,0.0001871282,0.9756246,0.01090875,0.001392307,0.001048106,0.00002305294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9264071,0.00141013,0.0674291,0.0004713914,0.0001117959,0.0002254941,0.0009794139,0.001315311,0.001650394],"genre_scores_gemma":[0.9540437,0.0001541519,0.04244515,0.0001445601,0.00002747656,0.0001635165,0.002318878,0.00007291364,0.0006296642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01089139,"threshold_uncertainty_score":0.0575999,"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."}}