{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003780819,0.0001071049,0.0001155085,0.00005794007,0.0005764574,0.001140725,0.0007599135,0.00008124646,0.00002541473],"category_scores_gemma":[0.0003629356,0.00009907245,0.00003193742,0.0001240085,0.00005959893,0.0006954502,0.0006327564,0.0002015775,0.00009310571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003096562,"about_ca_system_score_gemma":0.00003389657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001058384,"about_ca_topic_score_gemma":0.00004422188,"domain_scores_codex":[0.9988792,0.0000173324,0.0001113439,0.0003563533,0.0002669805,0.0003687682],"domain_scores_gemma":[0.9986258,0.0001344769,0.00003581672,0.001018847,0.00006306654,0.0001220604],"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":[0.00004110613,0.000191548,0.08022209,0.0001128978,0.00006047197,0.00007506296,0.001704582,0.0007621292,0.008455846,0.005018394,0.003355336,0.9000005],"study_design_scores_gemma":[0.001111251,0.0001900622,0.4274673,0.00004731854,0.000005386853,0.00007865985,0.00003656951,0.5305486,0.02562703,0.001200886,0.01320347,0.0004834378],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1821176,0.00006883033,0.8158847,0.0004772277,0.0002888462,0.0001178506,8.695493e-7,0.0004334934,0.0006106019],"genre_scores_gemma":[0.935146,0.00002097321,0.0622209,0.00005416767,0.00009154775,0.00001994607,3.977929e-7,0.00001256711,0.002433526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8995171,"threshold_uncertainty_score":0.9998962,"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."}}