{"id":"W1909497710","doi":"10.1007/s10664-015-9396-2","title":"Towards building a universal defect prediction model with rank transformed predictors","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"University of Victoria","keywords":"Computer science; Software; Rank (graph theory); Workflow; Predictive modelling; Context (archaeology); Eclipse; Data mining; Software development; Obstacle; Software bug; Software engineering; Machine learning; Database; Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004967626,0.0003470849,0.0003204588,0.0003532679,0.00008379864,0.0001488829,0.0008487701,0.0001723722,0.000004977282],"category_scores_gemma":[0.001311992,0.0003100125,0.0001347005,0.001145198,0.00004109129,0.0008990088,0.0001849057,0.0005304886,0.00001668784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005593395,"about_ca_system_score_gemma":0.0004254069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000223817,"about_ca_topic_score_gemma":0.000001645501,"domain_scores_codex":[0.997327,0.00003301994,0.0002783145,0.0006072115,0.0009985345,0.0007559236],"domain_scores_gemma":[0.9981569,0.0004277504,0.00003445291,0.000548059,0.000176637,0.000656223],"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":[0.00003941064,0.00004898979,0.04396766,0.00006089411,0.00009547183,0.00006731994,0.001214663,0.951546,0.0001250585,0.0003217549,0.0009971692,0.001515624],"study_design_scores_gemma":[0.001483678,0.000378046,0.0161956,0.000106886,0.00002944782,0.00008541723,0.00001483686,0.9768612,0.0008202167,0.0001529429,0.003359995,0.0005117554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2012297,0.00008754126,0.7953404,0.0001335339,0.0002904476,0.0002370241,0.000009530021,0.00263372,0.00003806324],"genre_scores_gemma":[0.7468565,0.000004900095,0.2528227,0.00003269863,0.0001165235,0.00004811522,0.000007085848,0.00005784303,0.0000536394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5456268,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02760184776548904,"score_gpt":0.2626829102734268,"score_spread":0.2350810625079377,"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."}}