{"id":"W3145055218","doi":"10.1109/iwsc.2012.6227875","title":"Shuffling and randomization for scalable source code clone detection","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; University of Saskatchewan; Concordia University","funders":"","keywords":"Shuffling; Computer science; Scalability; Code (set theory); Source code; clone (Java method); Key (lock); State (computer science); Theoretical computer science; Computer engineering; Data mining; Machine learning; Programming language; Database; Operating system","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":[0.006204037,0.00138049,0.001373699,0.003802182,0.0009180575,0.001827218,0.002661696,0.00132938,0.002031558],"category_scores_gemma":[0.03060113,0.0006967876,0.001198408,0.003180564,0.00120446,0.005030822,0.002344159,0.001623959,0.001783688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007767851,"about_ca_system_score_gemma":0.002018661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009236473,"about_ca_topic_score_gemma":0.001516896,"domain_scores_codex":[0.9912411,0.002814936,0.0007986648,0.002135976,0.002652056,0.0003571339],"domain_scores_gemma":[0.9697995,0.01234863,0.002622437,0.0129981,0.001836182,0.0003950192],"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":[0.0009855728,0.0004362797,0.01309899,0.0004874,0.0002752421,0.0004391851,0.0003877762,0.02839201,0.08464114,0.0147172,0.01633441,0.8398048],"study_design_scores_gemma":[0.0003409767,0.0009781857,0.007778328,0.0001142127,0.0001993879,0.001390966,0.000246931,0.6963714,0.219082,0.04313159,0.03010273,0.0002632523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05728826,0.0006173046,0.8955669,0.0002805986,0.000115841,0.000411093,0.0007664555,0.04361826,0.001335291],"genre_scores_gemma":[0.2768909,0.0002130318,0.7169247,0.0002572702,0.0001166423,0.0006178417,0.002325751,0.001389101,0.001264801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006204037,"threshold_uncertainty_score":0.03281051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647478806373406,"score_gpt":0.2557078956745717,"score_spread":0.2392331076108376,"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."}}