{"id":"W2095974519","doi":"10.1109/tse.2010.32","title":"Assessing, Comparing, and Combining State Machine-Based Testing and Structural Testing: A Series of Experiments","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Test strategy; Non-regression testing; Software performance testing; White-box testing; Machine learning; Reliability engineering; Model-based testing; Software testing; Risk-based testing; Software; Series (stratigraphy); Code coverage; State (computer science); Keyword-driven testing; Software reliability testing; Data mining; Test case; Software quality; Algorithm; Software system; Software development; Engineering; Software construction","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":[0.007070511,0.001882231,0.001360801,0.001241336,0.0004689528,0.0008518606,0.002129822,0.001753242,0.002139019],"category_scores_gemma":[0.03658542,0.0006741243,0.001120071,0.0008919677,0.001152671,0.002008854,0.001170871,0.001231777,0.0003588356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105869,"about_ca_system_score_gemma":0.001083854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001684385,"about_ca_topic_score_gemma":0.001675944,"domain_scores_codex":[0.9917631,0.004088154,0.000903682,0.00118006,0.001579183,0.0004857994],"domain_scores_gemma":[0.9114702,0.07438717,0.003889814,0.005821335,0.003445126,0.0009864353],"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":[0.05284751,0.0768852,0.02951685,0.003465664,0.001638902,0.0007389088,0.003403259,0.2880326,0.2355747,0.005620625,0.002859672,0.2994162],"study_design_scores_gemma":[0.0085663,0.2512597,0.03511932,0.0002332267,0.001391248,0.0006388863,0.001437558,0.4215034,0.2624623,0.008947087,0.007978274,0.0004625401],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786077,0.0002004681,0.01788528,0.00008590247,0.00005206577,0.001331595,0.0002882012,0.0002922184,0.001256693],"genre_scores_gemma":[0.9555268,0.0002049797,0.03990018,0.0001158065,0.00003880203,0.002380679,0.0006231075,0.00008808241,0.001121474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007070511,"threshold_uncertainty_score":0.03739291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03442196261994303,"score_gpt":0.2701052537879602,"score_spread":0.2356832911680171,"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."}}