{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01315021,0.003879452,0.001755994,0.01404869,0.00131673,0.004696232,0.005124886,0.002830743,0.003503961],"category_scores_gemma":[0.05546233,0.001501214,0.002590458,0.00624657,0.001731128,0.007081707,0.004863321,0.002222816,0.002421415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00222218,"about_ca_system_score_gemma":0.003059582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007363605,"about_ca_topic_score_gemma":0.006971311,"domain_scores_codex":[0.9818018,0.004794022,0.002744291,0.002613785,0.007321705,0.0007245122],"domain_scores_gemma":[0.9526215,0.02488182,0.004464408,0.007508738,0.009325706,0.001197793],"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":[0.00284156,0.002281759,0.08306343,0.005242383,0.001963228,0.001296721,0.00400197,0.04574897,0.05821622,0.01808927,0.1506405,0.6266141],"study_design_scores_gemma":[0.001428009,0.004016141,0.04302343,0.0009571306,0.0009477713,0.002528487,0.001596141,0.5916052,0.197378,0.02482242,0.1306329,0.001064409],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09712575,0.002003185,0.4833073,0.0004642039,0.0002372853,0.002078001,0.01399759,0.3938045,0.006982217],"genre_scores_gemma":[0.2334984,0.000526953,0.6928719,0.000617405,0.0001097421,0.00298646,0.04317844,0.02309803,0.003112626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9868498,"threshold_uncertainty_score":0.06954575,"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."}}