{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01285726,0.0006687521,0.0007455603,0.003691411,0.0006273522,0.001891293,0.001230192,0.0008388311,0.003828421],"category_scores_gemma":[0.08734357,0.0004444223,0.001169352,0.005860583,0.0007390566,0.002209198,0.002001188,0.001699106,0.002772951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000472762,"about_ca_system_score_gemma":0.001554305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00304235,"about_ca_topic_score_gemma":0.002480721,"domain_scores_codex":[0.9854428,0.008865234,0.001417139,0.001716173,0.002116905,0.0004418724],"domain_scores_gemma":[0.9202886,0.05620164,0.002634871,0.0151874,0.005214328,0.0004731547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002275468,0.0008916195,0.2012669,0.0004151607,0.0003538556,0.0003870676,0.000808296,0.01897589,0.007268714,0.006657164,0.009652003,0.7510478],"study_design_scores_gemma":[0.0003841655,0.0014722,0.1836613,0.0003631324,0.000462382,0.001732399,0.002628902,0.6834995,0.05852988,0.03975395,0.02735175,0.0001604311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5029914,0.0005153908,0.471227,0.0007831426,0.0002410167,0.000785501,0.008864594,0.009648155,0.004943741],"genre_scores_gemma":[0.8421451,0.0001157586,0.1468104,0.00008583666,0.00003377241,0.0004760697,0.008271557,0.0004577289,0.001603731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01285726,"threshold_uncertainty_score":0.0679965,"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."}}