{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004132118,0.0001506866,0.0001635363,0.00006937492,0.0001027322,0.0001540903,0.0005177393,0.00005887808,0.0000121126],"category_scores_gemma":[0.0003361534,0.0001105226,0.00003111686,0.0003145589,0.00004042397,0.0002265606,0.0001370558,0.0001359738,0.00006890502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000299135,"about_ca_system_score_gemma":0.00003591802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001534613,"about_ca_topic_score_gemma":0.000003454783,"domain_scores_codex":[0.9989675,0.00007549429,0.0001139788,0.0003755177,0.000224317,0.0002431359],"domain_scores_gemma":[0.9974527,0.001697931,0.00005836347,0.00060923,0.0001044926,0.00007723255],"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":[0.00009665208,0.0004770368,0.7536665,0.0001311378,0.00007387555,0.00007403986,0.0007159901,0.0006895232,0.001485468,0.03355272,0.03380033,0.1752367],"study_design_scores_gemma":[0.002469382,0.003221383,0.4012133,0.0004887831,0.00003335571,0.0002173164,0.000002145874,0.5158896,0.04486172,0.02579502,0.004464668,0.001343297],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04433278,0.00000509963,0.9402823,0.0001525712,0.00008539899,0.0001382851,0.000001430962,0.01046235,0.004539736],"genre_scores_gemma":[0.9325945,6.007951e-7,0.06644562,0.0005680937,0.00001979924,0.00001512123,0.00000132208,0.00001244459,0.0003424466],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8882618,"threshold_uncertainty_score":0.4506979,"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."}}