{"id":"W2158439356","doi":"10.1109/icsm.2015.7332459","title":"Evaluating clone detection tools with BigCloneBench","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"clone (Java method); Code refactoring; Benchmark (surveying); Java; Computer science; Precision and recall; Software; Similarity (geometry); Source code; Data mining; Software engineering; Artificial intelligence; Programming language; Biology; Genetics; Gene","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":[0.0190217,0.002508156,0.001367648,0.01575232,0.0009415227,0.004429682,0.004382661,0.003108435,0.0009963475],"category_scores_gemma":[0.1114341,0.0009377247,0.001737627,0.008120441,0.00146215,0.006067866,0.003953103,0.001481418,0.0008368986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001616876,"about_ca_system_score_gemma":0.002083776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004953224,"about_ca_topic_score_gemma":0.005792926,"domain_scores_codex":[0.9723388,0.005812797,0.004488592,0.00382801,0.01274669,0.0007851083],"domain_scores_gemma":[0.8351669,0.1054923,0.0136298,0.0222392,0.02111697,0.002354732],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001845658,0.001887316,0.312657,0.004862927,0.002212756,0.001742145,0.004903204,0.05643419,0.04048873,0.007222842,0.05298064,0.5127627],"study_design_scores_gemma":[0.0007870376,0.003542188,0.1092374,0.001110742,0.0009461552,0.004556049,0.002571175,0.664627,0.1420297,0.009375382,0.06044938,0.0007677321],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7120396,0.006534145,0.1659248,0.0008484843,0.0003903581,0.0007910038,0.01051311,0.09692804,0.006030427],"genre_scores_gemma":[0.6505093,0.001105954,0.3014919,0.0005907708,0.0001225565,0.0007652385,0.03976301,0.003594788,0.002056504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9809783,"threshold_uncertainty_score":0.1005976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1333061848911631,"score_gpt":0.3519736051383486,"score_spread":0.2186674202471855,"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."}}