{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05661387,0.001492559,0.002100821,0.01339136,0.002703586,0.009565821,0.003033736,0.004392758,0.006284188],"category_scores_gemma":[0.3691507,0.001200687,0.001068362,0.015168,0.01302212,0.02239318,0.004711918,0.007372558,0.003092468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002591869,"about_ca_system_score_gemma":0.003729711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00417027,"about_ca_topic_score_gemma":0.003526899,"domain_scores_codex":[0.9371637,0.0210214,0.002864819,0.007950653,0.03038885,0.0006107182],"domain_scores_gemma":[0.4094855,0.4789419,0.03113143,0.04132102,0.03532764,0.00379242],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008278509,0.0004134402,0.09216855,0.004570646,0.0008911192,0.0002992474,0.002014329,0.01026538,0.001491953,0.1472797,0.1317831,0.6079947],"study_design_scores_gemma":[0.000214524,0.0008291411,0.05268865,0.005676197,0.0003329997,0.001261979,0.002614863,0.03832136,0.002915649,0.6948282,0.199894,0.0004224851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.08831549,0.2594612,0.2232922,0.3574788,0.01396161,0.0003601053,0.008050736,0.001914041,0.04716587],"genre_scores_gemma":[0.7221677,0.1164358,0.08245356,0.03676503,0.02365739,0.0005885656,0.00396922,0.0009519453,0.01301086],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9433861,"threshold_uncertainty_score":0.2994063,"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."}}