{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004234893,0.0001322921,0.0001106244,0.0002092674,0.0002534242,0.0001231913,0.000270666,0.00008050734,0.00001272322],"category_scores_gemma":[0.00187297,0.0001217729,0.00002752179,0.0008651432,0.00009722594,0.000166944,0.0002156991,0.0001443554,0.00006225174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004810454,"about_ca_system_score_gemma":0.00009618677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001509745,"about_ca_topic_score_gemma":0.00001654565,"domain_scores_codex":[0.9988022,0.00006009314,0.0001575303,0.0004340963,0.0002817544,0.0002643357],"domain_scores_gemma":[0.9958421,0.003372666,0.00003275297,0.0005098109,0.0001305353,0.0001121457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001359612,0.0006632686,0.4143102,0.0001253226,0.000009521098,0.002952657,0.0006023903,0.007364617,0.0001695397,0.002085847,0.5507798,0.02092326],"study_design_scores_gemma":[0.0001767281,0.0002245363,0.0206219,0.00003731644,0.000003061812,0.0001755381,0.000006800637,0.9744878,0.0003631312,0.003501293,0.0002401185,0.0001617535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05295454,0.00003005296,0.8866823,0.009734902,0.0001781352,0.0005823857,0.00007898605,0.04548908,0.004269663],"genre_scores_gemma":[0.8127243,0.000005637907,0.1860905,0.0006969166,0.00003520105,0.00001421561,0.00001567088,0.00001254553,0.0004049843],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9671232,"threshold_uncertainty_score":0.4965755,"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."}}