{"id":"W4384345653","doi":"10.1109/icse48619.2023.00146","title":"ATM: Black-box Test Case Minimization based on Test Code Similarity and Evolutionary Search","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test suite; Code coverage; Test case; Abstract syntax tree; Fault coverage; Scalability; Minification; Similarity (geometry); Automatic test pattern generation; Test (biology); Java; Regression testing; Syntax; Programming language; Software; Artificial intelligence; Machine learning; Software development; Operating system; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002144721,0.001645922,0.001486365,0.004475483,0.0004883498,0.001030801,0.00265395,0.001341997,0.002356748],"category_scores_gemma":[0.010977,0.0005655015,0.001801949,0.002552363,0.001038576,0.001553022,0.001560692,0.000965537,0.0006413974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009725555,"about_ca_system_score_gemma":0.001710918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003111613,"about_ca_topic_score_gemma":0.002970741,"domain_scores_codex":[0.9964699,0.0009767894,0.000241965,0.0006473237,0.001446875,0.0002172844],"domain_scores_gemma":[0.995079,0.002627343,0.0007980379,0.0007676606,0.0005704617,0.0001573646],"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":[0.000568358,0.0005429219,0.01128779,0.0005395828,0.0004059279,0.0003582036,0.0002060265,0.3263327,0.02814671,0.01005187,0.006240394,0.6153196],"study_design_scores_gemma":[0.00009228667,0.0003063636,0.001959383,0.000032336,0.00007476546,0.0003006085,0.00003392774,0.9823201,0.00776732,0.005100077,0.001992874,0.00001985866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07816901,0.0009179928,0.9086822,0.0002261905,0.0000446362,0.0005738476,0.0004326726,0.008549668,0.002403834],"genre_scores_gemma":[0.3836293,0.0002172989,0.6107196,0.0001862569,0.00005069937,0.0007537543,0.002168108,0.0006947787,0.001580255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004475483,"threshold_uncertainty_score":0.01134253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04103145356441748,"score_gpt":0.29445215780039,"score_spread":0.2534207042359725,"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."}}