{"id":"W4319264802","doi":"10.1016/j.infsof.2023.107169","title":"Just-in-time code duplicates extraction","year":2023,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Code refactoring; Computer science; Plug-in; Workflow; Program slicing; Artificial intelligence; Source code; Machine learning; Software engineering; Deep learning; Coding (social sciences); Code review; Classifier (UML); Software maintenance; Convolutional neural network; Software; Static program analysis; Programming language; Software development; Database","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":[0.001353781,0.001954244,0.001790738,0.00467794,0.001709109,0.003275255,0.002963911,0.001629801,0.009482614],"category_scores_gemma":[0.01664594,0.0009335939,0.002247276,0.003608332,0.0008263506,0.004475105,0.004131313,0.001397338,0.009179757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007967307,"about_ca_system_score_gemma":0.00518057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00291096,"about_ca_topic_score_gemma":0.005974463,"domain_scores_codex":[0.9941657,0.0006074822,0.0005611737,0.001011842,0.003126279,0.0005275938],"domain_scores_gemma":[0.9855816,0.003045892,0.0008556741,0.005763393,0.004413008,0.0003403888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007343833,0.0001709401,0.004481143,0.001525244,0.0002158161,0.001153714,0.0005262101,0.004488677,0.05408075,0.01395982,0.06035347,0.8583099],"study_design_scores_gemma":[0.0003025949,0.0006429669,0.008483179,0.0004693388,0.0006778218,0.006591404,0.001311622,0.2553264,0.3761458,0.08819899,0.2614864,0.0003636401],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04723328,0.001658753,0.8835029,0.0009286315,0.001136022,0.0006834851,0.00618612,0.04872809,0.009942824],"genre_scores_gemma":[0.197216,0.0008712372,0.7540732,0.0004917858,0.0003428066,0.0003264383,0.01658566,0.006900824,0.02319215],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009482614,"threshold_uncertainty_score":0.03172255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01338013561787999,"score_gpt":0.2740174389974117,"score_spread":0.2606373033795317,"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."}}