{"id":"W2101832700","doi":"10.1016/j.scico.2009.02.007","title":"Comparison and evaluation of code clone detection techniques and tools: A qualitative approach","year":2009,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Engineering Research","field":"Computer Science","cited_by":1002,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; clone (Java method); Schema (genetic algorithms); Taxonomy (biology); Set (abstract data type); Source code; Context (archaeology); Data mining; Software engineering; Artificial intelligence; Programming language; Information retrieval","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":[0.06751613,0.0009250151,0.001252711,0.01042756,0.003314513,0.003911766,0.00272869,0.001492608,0.003521432],"category_scores_gemma":[0.1885977,0.0006571646,0.0008824534,0.006134626,0.003738722,0.004539489,0.003357158,0.001176953,0.0003958225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01035605,"about_ca_system_score_gemma":0.008320644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005362688,"about_ca_topic_score_gemma":0.008035923,"domain_scores_codex":[0.920544,0.05109779,0.004268378,0.002386802,0.01968436,0.002018739],"domain_scores_gemma":[0.6118573,0.2841516,0.01165211,0.006570915,0.08381553,0.001952553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.004674595,0.003157068,0.06038065,0.01909419,0.0005671383,0.0008507641,0.2653497,0.007058442,0.05505494,0.03810852,0.005716073,0.5399879],"study_design_scores_gemma":[0.001551412,0.01756948,0.1371625,0.01041809,0.002172018,0.001629485,0.5069697,0.03805796,0.178806,0.03920225,0.06571417,0.0007469126],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8260685,0.00226788,0.1285611,0.002345588,0.0001311666,0.00757683,0.002049899,0.0003472939,0.03065179],"genre_scores_gemma":[0.9351101,0.0007325293,0.0572611,0.0002382839,0.00002055432,0.00343681,0.00035184,0.0001153071,0.002733572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06751613,"threshold_uncertainty_score":0.3570637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09302423369983133,"score_gpt":0.4135048661088837,"score_spread":0.3204806324090523,"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."}}