{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002047044,0.0002498549,0.0002669888,0.0002322417,0.0002276613,0.0002504263,0.0002496095,0.00006804038,0.000001307105],"category_scores_gemma":[0.0003611732,0.0002575731,0.00003135123,0.0003673845,0.00008655653,0.0005605597,0.00001274482,0.0004367653,3.938235e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001850937,"about_ca_system_score_gemma":0.00004971608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001331375,"about_ca_topic_score_gemma":0.000005732027,"domain_scores_codex":[0.998856,0.00002133928,0.0002893251,0.0003610036,0.0002014286,0.0002708962],"domain_scores_gemma":[0.9983659,0.0009494651,0.0001150324,0.000339351,0.000107279,0.0001229878],"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":[0.00005500861,0.0003231107,0.357921,0.001037836,0.0001794196,0.00009353434,0.003386018,0.2102569,0.09151922,0.0002668356,0.00006149194,0.3348996],"study_design_scores_gemma":[0.0004923505,0.0002171204,0.02136008,0.0003291891,0.00001587191,0.0001510745,0.000006315396,0.924264,0.05238759,0.000353868,0.000008774798,0.0004137967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4155685,0.00002696781,0.5812519,0.000005662471,0.0002140006,0.00007138895,0.000003397576,0.002851572,0.000006619748],"genre_scores_gemma":[0.541153,3.908802e-7,0.4587967,0.00001109829,0.000006207893,0.00001233486,3.704985e-7,0.00001688543,0.000002999709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7140071,"threshold_uncertainty_score":0.9999877,"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."}}