{"id":"W4313563578","doi":"10.1145/3551349.3559537","title":"AntiCopyPaster: Extracting Code Duplicates As Soon As They Are Introduced in the IDE","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Code refactoring; Computer science; Plug-in; Programming language; Code (set theory); Workflow; Source code; Fragment (logic); Software engineering; Database; Software; Set (abstract data type)","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":[0.005301556,0.002322128,0.001498185,0.004552486,0.001045291,0.00309676,0.00322542,0.001718222,0.00403868],"category_scores_gemma":[0.02803345,0.001784256,0.001510507,0.001568934,0.001009512,0.00430644,0.002558846,0.002756224,0.003771205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008994309,"about_ca_system_score_gemma":0.003615989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00407489,"about_ca_topic_score_gemma":0.008107359,"domain_scores_codex":[0.9944317,0.000524206,0.0005152033,0.001621304,0.002566428,0.0003412058],"domain_scores_gemma":[0.9773006,0.009962376,0.003192095,0.005646006,0.003352788,0.0005462306],"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":[0.00100786,0.0005080039,0.04198181,0.00189063,0.0002447076,0.001043196,0.002571858,0.008102429,0.04863404,0.009008827,0.06920424,0.8158024],"study_design_scores_gemma":[0.0002945979,0.000797624,0.02652772,0.0007028684,0.000463594,0.002661186,0.0007328881,0.4021716,0.2791226,0.01650941,0.2694995,0.0005165204],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04683753,0.0008045135,0.6238523,0.0004851757,0.0003378616,0.0007628074,0.004546067,0.3169559,0.005417936],"genre_scores_gemma":[0.1196704,0.0004046302,0.8361837,0.0003923661,0.0001093755,0.0004816623,0.01081595,0.02160906,0.01033289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005301556,"threshold_uncertainty_score":0.02803761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0228698490153916,"score_gpt":0.2916818676221686,"score_spread":0.2688120186067771,"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."}}