{"id":"W2605594016","doi":"10.1007/s10664-017-9516-2","title":"Data Transformation in Cross-project Defect Prediction","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Transformation (genetics); Computer science; Data mining; Data transformation; Software; Rank (graph theory); Predictive modelling; Reliability engineering; Machine learning; Data warehouse; Mathematics; Engineering","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":[0.0008426551,0.0001998896,0.0002009036,0.000272166,0.0002107804,0.000693896,0.002956094,0.0001388484,0.000006466819],"category_scores_gemma":[0.005576007,0.000204207,0.00006931787,0.0003379153,0.00003358821,0.002774355,0.0007660612,0.0004588681,0.00003921494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656395,"about_ca_system_score_gemma":0.0000883539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009053733,"about_ca_topic_score_gemma":0.00001522737,"domain_scores_codex":[0.9980905,0.00002515838,0.0003243227,0.0005734624,0.0004723774,0.0005141615],"domain_scores_gemma":[0.9969677,0.0005777204,0.00005223861,0.002236812,0.00005146135,0.000114034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008707912,0.00005305709,0.9460662,0.0001272857,0.00002699399,0.00005637147,0.0005009759,0.04333401,0.00006402205,0.0001662995,0.0008515659,0.008744516],"study_design_scores_gemma":[0.0003631155,0.00002938774,0.7375204,0.00005100452,0.000002277422,0.00001537251,0.000001320225,0.256253,0.00009609805,0.00002203363,0.005468369,0.0001775797],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2542563,0.0001023149,0.7437317,0.0001401504,0.0005769487,0.0002198313,0.00003708673,0.0008987694,0.00003690772],"genre_scores_gemma":[0.959863,0.00001743026,0.03979487,0.00001939534,0.0001566691,0.00004397484,0.00004400021,0.00003053891,0.00003012517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7056067,"threshold_uncertainty_score":0.8327318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08894280679107658,"score_gpt":0.3731778103193423,"score_spread":0.2842350035282658,"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."}}