{"id":"W2621103691","doi":"10.1109/icse-c.2017.78","title":"CloneWorks: A Fast and Flexible Large-Scale Near-Miss Clone Detection Tool","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"clone (Java method); Computer science; Scalability; Workstation; Source code; Detector; Precision and recall; Code (set theory); Operating system; Artificial intelligence; Programming language; 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":[],"consensus_categories":[],"category_scores_codex":[0.002594559,0.001887327,0.001458622,0.005285238,0.001045321,0.002167892,0.003194429,0.002171778,0.005313864],"category_scores_gemma":[0.01678681,0.001391483,0.001243049,0.00355079,0.00091851,0.004557576,0.003143359,0.001342054,0.004741416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000906872,"about_ca_system_score_gemma":0.001873086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003419524,"about_ca_topic_score_gemma":0.004589581,"domain_scores_codex":[0.9958259,0.0004530164,0.0003197604,0.0009938092,0.002173724,0.0002337968],"domain_scores_gemma":[0.9880019,0.004489767,0.001335788,0.003388968,0.00225192,0.0005315993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001307869,0.0003409022,0.01762677,0.0009010665,0.0004998247,0.001085225,0.001004522,0.008869783,0.1490071,0.005617877,0.1128432,0.700896],"study_design_scores_gemma":[0.001269679,0.001589284,0.02460304,0.0002868801,0.0005504692,0.003428025,0.0007296219,0.3698052,0.403839,0.02601954,0.1672375,0.0006417067],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03930636,0.0009682641,0.5176126,0.0002180902,0.0001589733,0.000396561,0.003888362,0.4340695,0.003381263],"genre_scores_gemma":[0.2353666,0.0005272591,0.7108116,0.0004641889,0.000126624,0.001042274,0.01901453,0.02345036,0.009196645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005313864,"threshold_uncertainty_score":0.01777667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01373259112381605,"score_gpt":0.2698143242420956,"score_spread":0.2560817331182796,"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."}}