{"id":"W2909172538","doi":"10.1109/tse.2019.2891758","title":"The Impact of Correlated Metrics on the Interpretation of Defect Models","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Australian Research Council","keywords":"Consistency (knowledge bases); Ranking (information retrieval); Interpretation (philosophy); Computer science; Metric (unit); Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04328036,0.00204995,0.001699579,0.006275942,0.001046094,0.005392224,0.001875413,0.001364361,0.001032381],"category_scores_gemma":[0.2853576,0.000909962,0.002296627,0.004675769,0.002626546,0.005661291,0.003244873,0.003340949,0.000471368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002284733,"about_ca_system_score_gemma":0.00265622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00323079,"about_ca_topic_score_gemma":0.004661975,"domain_scores_codex":[0.924652,0.04182934,0.005449464,0.008062754,0.01897414,0.001032183],"domain_scores_gemma":[0.5389713,0.33771,0.0375033,0.05726302,0.0271081,0.001444347],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001396241,0.0004236394,0.3400559,0.001791769,0.002403739,0.001022628,0.003224571,0.2307954,0.01563507,0.02609401,0.007756543,0.3694004],"study_design_scores_gemma":[0.0002283128,0.001551411,0.152965,0.0009763682,0.001209497,0.001817636,0.002523826,0.675308,0.02680261,0.1221786,0.01395881,0.0004798193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.490131,0.003079107,0.492663,0.00179003,0.0003064277,0.0003061302,0.002049135,0.002973091,0.00670212],"genre_scores_gemma":[0.8689774,0.0003889625,0.1266568,0.0002722896,0.00008461954,0.0001160637,0.002318172,0.0007735912,0.000411933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9567196,"threshold_uncertainty_score":0.2288912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142771819316302,"score_gpt":0.2477259451862916,"score_spread":0.2334487632546614,"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."}}