{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007496798,0.00007412071,0.00007118056,0.00009652722,0.00004276659,0.0001967781,0.0003877862,0.00002966248,0.000009494988],"category_scores_gemma":[0.0009060833,0.00005639067,0.00001312702,0.0005724952,0.00001466402,0.0005131871,0.0001395118,0.0001160101,0.0001287762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008111834,"about_ca_system_score_gemma":0.0001140943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007377849,"about_ca_topic_score_gemma":0.00001245013,"domain_scores_codex":[0.9988144,0.00003642134,0.00008955251,0.0002392909,0.0005914074,0.0002289101],"domain_scores_gemma":[0.9989439,0.0002873836,0.00001858569,0.0004109626,0.0002034585,0.0001357645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003182101,0.0000739967,0.009221844,0.00002498026,0.00003681102,0.00004763233,0.001079501,0.02322485,0.01596736,0.003667986,0.0008228713,0.9458004],"study_design_scores_gemma":[0.001715245,0.00196285,0.03924775,0.00003998002,0.000006816333,0.000199289,0.00008957733,0.8594953,0.09419079,0.001144912,0.001340167,0.0005673293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2978311,0.00002403798,0.7006338,0.0001109105,0.0001273775,0.00008938849,8.694923e-8,0.0004189707,0.0007642838],"genre_scores_gemma":[0.8341037,4.400781e-7,0.1653982,0.00002810161,0.00004918693,0.00002081216,3.363436e-7,0.000007089408,0.0003921284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.945233,"threshold_uncertainty_score":0.2299545,"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."}}