{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004765686,0.000176282,0.000194467,0.0003520582,0.00007234103,0.00004820214,0.0007616205,0.00007854841,0.00001092371],"category_scores_gemma":[0.0003186275,0.0001105853,0.0003021005,0.001306069,0.00002780749,0.0002334267,0.000006554667,0.0004518231,0.00002087806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492353,"about_ca_system_score_gemma":0.00006818798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003851951,"about_ca_topic_score_gemma":6.735598e-7,"domain_scores_codex":[0.9987307,0.00004848371,0.0002847062,0.0002167602,0.0004537685,0.0002655583],"domain_scores_gemma":[0.9935035,0.005448703,0.00007557564,0.0007644931,0.00015238,0.00005534209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002131445,0.00003489848,0.000124693,0.00002042685,0.0001161587,5.844882e-7,0.0002835463,0.9922028,0.0004010091,0.0004393793,0.00001921351,0.006335969],"study_design_scores_gemma":[0.0001717318,0.0002919654,0.001041474,0.00009966643,0.000009291133,0.00000422041,0.000008951563,0.9875055,0.01069144,0.00005886351,0.000005087831,0.0001117846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1896293,0.00007837362,0.8093151,0.0000122192,0.000491519,0.0002473208,0.000007930679,0.0002027891,0.00001546684],"genre_scores_gemma":[0.99628,0.0000264851,0.003579485,0.000004358802,0.000006544725,0.00002808204,4.577971e-7,0.00002675548,0.00004784348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8066507,"threshold_uncertainty_score":0.4509536,"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."}}