{"id":"W2025962632","doi":"10.1109/icsme.2014.54","title":"Evaluating Modern Clone Detection Tools","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"clone (Java method); Benchmark (surveying); Computer science; Precision and recall; Cloning (programming); Software maintenance; Matching (statistics); Code (set theory); Software; Code refactoring; Software engineering; Machine learning; Artificial intelligence; Data mining; Software system; Programming language; Biology; Genetics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03600228,0.002141275,0.001429176,0.01923999,0.001471269,0.0047178,0.005122008,0.00363758,0.001231452],"category_scores_gemma":[0.1462568,0.0008536698,0.001779107,0.008186048,0.001458079,0.006465477,0.00475427,0.001563793,0.0009014683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004461081,"about_ca_system_score_gemma":0.003973989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01488767,"about_ca_topic_score_gemma":0.01696313,"domain_scores_codex":[0.9307902,0.01538661,0.008024585,0.009583535,0.03394185,0.002273211],"domain_scores_gemma":[0.8010332,0.1015041,0.01878651,0.02321939,0.05216711,0.003289696],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001157106,0.001043213,0.1731646,0.002977113,0.001194699,0.0005742157,0.00644299,0.02494997,0.02147113,0.007797735,0.02520609,0.7340211],"study_design_scores_gemma":[0.0007074727,0.004665644,0.2328762,0.002201407,0.001457688,0.003880095,0.005993622,0.4938172,0.0922315,0.01363003,0.147484,0.001055164],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7565725,0.01058501,0.1744035,0.001296391,0.000497152,0.001079149,0.004791031,0.03809683,0.01267842],"genre_scores_gemma":[0.6218393,0.001477153,0.353843,0.0005470419,0.0001339057,0.0005316274,0.01657937,0.001865758,0.003182827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9639977,"threshold_uncertainty_score":0.1904005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07222274584709264,"score_gpt":0.3402158347236393,"score_spread":0.2679930888765467,"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."}}