{"id":"W2796141603","doi":"10.1109/saner.2018.8330194","title":"Benchmarks for software clone detection: A ten-year retrospective","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"clone (Java method); Benchmark (surveying); Java; Computer science; Source lines of code; Software maintenance; Cloning (programming); Software; Software engineering; Precision and recall; Code refactoring; Set (abstract data type); Empirical research; Source code; Code (set theory); Software system; Programming language; Machine learning; Statistics; Biology","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":[0.04421092,0.002735949,0.002352919,0.02627674,0.002479594,0.00742941,0.006297709,0.0021926,0.002321806],"category_scores_gemma":[0.1822069,0.001503034,0.002370672,0.02576966,0.002472271,0.009177858,0.006312492,0.004571481,0.003160793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007049712,"about_ca_system_score_gemma":0.005641703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01383201,"about_ca_topic_score_gemma":0.01684612,"domain_scores_codex":[0.9360315,0.01241055,0.007894308,0.009686862,0.03171655,0.002260282],"domain_scores_gemma":[0.7111301,0.08232217,0.02448241,0.03446013,0.1393877,0.008217472],"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":[0.0008263298,0.0007075453,0.1113199,0.006278109,0.0008191076,0.000266034,0.001350445,0.00735663,0.004014965,0.01234226,0.3022245,0.5524942],"study_design_scores_gemma":[0.0002253878,0.001725323,0.1916156,0.00808041,0.0008821816,0.00204272,0.002163889,0.02450503,0.02299972,0.01231337,0.7329223,0.0005241854],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3258,0.2580023,0.1302719,0.01661229,0.006733977,0.002394513,0.1769312,0.03062133,0.05263247],"genre_scores_gemma":[0.3220652,0.04793841,0.1367048,0.005203329,0.001179346,0.003159222,0.4693242,0.006347252,0.00807819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04421092,"threshold_uncertainty_score":0.2338125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01173961851561382,"score_gpt":0.2597864749169241,"score_spread":0.2480468564013102,"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."}}