{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002714518,0.0000745369,0.00009210969,0.001076184,0.00005803023,0.00009197263,0.0004337887,0.0001498816,0.00001007979],"category_scores_gemma":[0.0008617058,0.00007597815,0.00001293108,0.00147898,0.00004367216,0.000986518,0.0002482604,0.0001930945,0.001026426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003959975,"about_ca_system_score_gemma":0.00002636018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006906829,"about_ca_topic_score_gemma":0.000001958625,"domain_scores_codex":[0.9992731,0.000007140193,0.000196521,0.0001210927,0.0001657981,0.0002364109],"domain_scores_gemma":[0.9993392,0.0002405525,0.00003893096,0.0002878665,0.00005625312,0.00003718702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000763864,0.00002859295,0.1391044,0.00009366724,0.00001330212,0.00002843981,0.001018281,0.0009579884,0.0004119505,0.01936032,0.006209845,0.8327656],"study_design_scores_gemma":[0.001871179,0.0002538054,0.5827523,0.0001065448,0.00000516433,0.0003528523,0.0002916619,0.221118,0.005899578,0.02289401,0.1635611,0.0008937499],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5837142,0.00007536964,0.4016971,0.004655511,0.0002135332,0.0003018279,0.000005412545,0.009188433,0.0001485812],"genre_scores_gemma":[0.9738649,0.0001415495,0.0253601,0.0002093661,0.00001461511,0.0001217658,0.00002605231,0.00001016223,0.0002515666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8318718,"threshold_uncertainty_score":0.9997514,"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."}}