{"id":"W4308623347","doi":"10.1145/3550356.3561566","title":"An investigation into the effect of cluster-based preprocessing on software migration","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Preprocessor; Partition (number theory); Obsolescence; Data mining; Artificial intelligence; Set (abstract data type); Software; Programming language; Transformation (genetics); Natural language processing; Theoretical computer science; Machine learning","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":[0.002827727,0.0008585901,0.0007293195,0.001126966,0.00120214,0.001349957,0.001933343,0.0007865079,0.00246864],"category_scores_gemma":[0.02192032,0.000396627,0.0009495604,0.002242959,0.001018904,0.001715287,0.0007522406,0.001387569,0.0006118643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001203739,"about_ca_system_score_gemma":0.001640241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006821373,"about_ca_topic_score_gemma":0.006942072,"domain_scores_codex":[0.9972492,0.001070185,0.0002299153,0.0005040083,0.0006452735,0.0003014411],"domain_scores_gemma":[0.9626172,0.02171479,0.002279561,0.009096799,0.003919903,0.0003717505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003952342,0.002900482,0.03522569,0.001017197,0.0004447284,0.0007707442,0.00181324,0.1779342,0.1802015,0.009306704,0.003367367,0.5830659],"study_design_scores_gemma":[0.0002820103,0.003228251,0.04825567,0.00009411506,0.000486263,0.001017642,0.001433916,0.5571207,0.3664744,0.01086852,0.01060455,0.0001340098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7683434,0.0004577348,0.220214,0.0007092169,0.0001297561,0.0005720392,0.0003181037,0.004298725,0.004956938],"genre_scores_gemma":[0.8362934,0.0001860061,0.1613989,0.0001767223,0.00002591091,0.0001207846,0.0003712386,0.0003499004,0.001077181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006821373,"threshold_uncertainty_score":0.01495469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01083162283609999,"score_gpt":0.2678352767336775,"score_spread":0.2570036538975775,"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."}}