{"id":"W2002559933","doi":"","title":"Shuffling and randomization for scalable source code clone detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Concordia University","funders":"","keywords":"Shuffling; Computer science; Scalability; Code (set theory); Source code; clone (Java method); Machine learning; Theoretical computer science; Programming language; Database","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":[0.005096725,0.0009873708,0.0009608421,0.00345395,0.000789316,0.001714127,0.002206096,0.001138428,0.001673081],"category_scores_gemma":[0.02509513,0.000475594,0.0009750173,0.002889327,0.001152917,0.003493345,0.002270634,0.00152607,0.001345405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007672551,"about_ca_system_score_gemma":0.001597851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001003628,"about_ca_topic_score_gemma":0.00128512,"domain_scores_codex":[0.9928805,0.002327912,0.0006116593,0.001687836,0.002144083,0.000347923],"domain_scores_gemma":[0.9707865,0.01139788,0.002929074,0.01211122,0.002268621,0.0005067255],"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":[0.001254639,0.0006428459,0.03410382,0.0004476044,0.0003494814,0.0005231708,0.000453702,0.03833896,0.11557,0.01307267,0.01935837,0.7758848],"study_design_scores_gemma":[0.0001942688,0.0007360809,0.00862013,0.00007345062,0.0001154163,0.0009140132,0.0002006305,0.7828838,0.1678097,0.02285893,0.0154637,0.0001299552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1156142,0.00086953,0.8376117,0.0004044903,0.0001631691,0.0004258278,0.0009003516,0.04230721,0.001703453],"genre_scores_gemma":[0.4909476,0.0001814737,0.5039414,0.0002896822,0.0001298182,0.000476959,0.001888109,0.001014487,0.0011306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005096725,"threshold_uncertainty_score":0.02695435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01251566139029577,"score_gpt":0.2410320729598843,"score_spread":0.2285164115695885,"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."}}