{"id":"W2541219092","doi":"10.1109/ms.2016.156","title":"The Tragedy of Defect Prediction, Prince of Empirical Software Engineering Research","year":2016,"lang":"en","type":"article","venue":"IEEE Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Software bug; Computer science; Field (mathematics); Tragedy (event); Empirical research; Software; Software engineering; Data science; Engineering; Programming language; Mathematics; Sociology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002308158,0.0001875021,0.0002633335,0.0003067169,0.0002844035,0.0000459726,0.001971463,0.000138249,0.000008423533],"category_scores_gemma":[0.01407487,0.0001170182,0.0001777943,0.001240373,0.0002788328,0.0003221479,0.0005257177,0.0004268181,0.00002283934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001494279,"about_ca_system_score_gemma":0.000306377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001265417,"about_ca_topic_score_gemma":0.000003212085,"domain_scores_codex":[0.9967406,0.0001939682,0.0004898147,0.000490621,0.001372274,0.0007127248],"domain_scores_gemma":[0.9865599,0.0110264,0.00008975529,0.001391529,0.0007556123,0.0001768051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007260763,0.0002440509,0.8607714,0.0005417657,0.000252117,0.0000497096,0.002280736,0.003364902,0.01341327,0.001476835,0.007843711,0.1096889],"study_design_scores_gemma":[0.002017423,0.001226057,0.799156,0.00137226,0.00002634831,0.0000854443,0.00004574495,0.002649082,0.1613283,0.002179141,0.02907397,0.0008402168],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.296317,0.0004728641,0.7016551,0.0002261802,0.0005332236,0.0002814431,0.00002567828,0.0004817793,0.000006750427],"genre_scores_gemma":[0.970333,0.0000954323,0.02902983,0.000007333227,0.0001249818,0.00007886952,7.644693e-7,0.00004032759,0.0002894966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.674016,"threshold_uncertainty_score":0.99423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04349038948750195,"score_gpt":0.3262267852231912,"score_spread":0.2827363957356892,"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."}}