{"id":"W2106072155","doi":"10.1145/2568225.2568271","title":"Coverage is not strongly correlated with test suite effectiveness","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":398,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Test suite; Suite; Computer science; Proxy (statistics); Test (biology); Confounding; Test case; Statistics; Data mining; Machine learning; Mathematics; Regression analysis; Geology; Geography","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":[0.01239843,0.0007505367,0.001197942,0.004840515,0.0003535021,0.00211816,0.001124419,0.001325452,0.003066745],"category_scores_gemma":[0.2781792,0.000629343,0.001124094,0.003668169,0.001480655,0.003488568,0.001583485,0.001864594,0.000964816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009791044,"about_ca_system_score_gemma":0.0008200747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002069494,"about_ca_topic_score_gemma":0.002060566,"domain_scores_codex":[0.9697632,0.008215898,0.003070915,0.004101339,0.01292686,0.001921789],"domain_scores_gemma":[0.4663228,0.4363829,0.05638976,0.01444244,0.02148316,0.004978943],"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":[0.0005141038,0.0001314062,0.9465784,0.0003841924,0.001149146,0.0003243153,0.0002999493,0.008851292,0.002352961,0.000982551,0.001413948,0.03701774],"study_design_scores_gemma":[0.00003195093,0.0005581657,0.9708583,0.0001473919,0.0004636299,0.001233998,0.0002240738,0.01794206,0.002527745,0.003978797,0.001980738,0.00005316856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9579586,0.004813873,0.0217529,0.001251169,0.00009558294,0.0001033302,0.001735916,0.0007169973,0.01157165],"genre_scores_gemma":[0.9969276,0.0002541098,0.00136371,0.00009800543,0.000048491,0.00003046355,0.0008495739,0.0001221869,0.0003059609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01239843,"threshold_uncertainty_score":0.06557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008925411068723877,"score_gpt":0.22585647833184,"score_spread":0.2169310672631161,"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."}}