{"id":"W2578208870","doi":"10.1109/icsme.2016.62","title":"BigCloneEval: A Clone Detection Tool Evaluation Framework with BigCloneBench","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"clone (Java method); Java; Computer science; Benchmark (surveying); Precision and recall; Open source; Software; Software engineering; Variety (cybernetics); Operating system; Artificial intelligence; Biology; 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":[0.0009863919,0.0001467666,0.0001186342,0.0002320988,0.00008689101,0.0001326303,0.0005433888,0.0001006297,0.0001450646],"category_scores_gemma":[0.001484379,0.00008644938,0.00003617617,0.0009343947,0.00004052005,0.0006084903,0.0001398205,0.0001465581,0.0003004853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001925222,"about_ca_system_score_gemma":0.0001293975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003523965,"about_ca_topic_score_gemma":0.00001282321,"domain_scores_codex":[0.9978231,0.00008556952,0.0001686645,0.0004698552,0.001077289,0.0003754921],"domain_scores_gemma":[0.9977167,0.0009684859,0.00004222104,0.0008458378,0.0003269761,0.00009974084],"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":[0.00003828758,0.00007674095,0.008683414,0.00001921256,0.00004991909,0.00001428808,0.0002482345,0.0004306806,0.02896121,0.01103137,0.0003269588,0.9501197],"study_design_scores_gemma":[0.005675921,0.002303045,0.3886726,0.0007020391,0.00006583121,0.0003173024,0.0000406893,0.1992458,0.3611161,0.03439182,0.005244797,0.002224127],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2456937,0.00003877276,0.7523797,0.0006268843,0.000241878,0.0002583042,4.185527e-7,0.0005989702,0.0001614184],"genre_scores_gemma":[0.9129021,0.000009404678,0.08648654,0.00005298741,0.000100743,0.000121017,3.448457e-7,0.00001772003,0.0003091481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9478955,"threshold_uncertainty_score":0.386223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01987006014401904,"score_gpt":0.2768289316468394,"score_spread":0.2569588715028203,"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."}}