{"id":"W2100060170","doi":"10.1109/icstw.2009.18","title":"A Mutation/Injection-Based Automatic Framework for Evaluating Code Clone Detection Tools","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":195,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"clone (Java method); Computer science; Benchmark (surveying); Precision and recall; Software; Software maintenance; Code (set theory); Data mining; Mutation; Machine learning; Software system; Software engineering; Artificial intelligence; Programming language; Set (abstract data type); Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006910003,0.0001032317,0.0001091598,0.0001724281,0.0001688043,0.000278669,0.0003330593,0.00007818628,0.00002303042],"category_scores_gemma":[0.005405232,0.0001015559,0.00006153449,0.0006377807,0.000009994942,0.0003371846,0.00001972737,0.0001479895,0.00003348824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344039,"about_ca_system_score_gemma":0.000111187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008290058,"about_ca_topic_score_gemma":0.000003272571,"domain_scores_codex":[0.9987758,0.00004523667,0.0002053612,0.0002943923,0.0004028517,0.0002763978],"domain_scores_gemma":[0.9961866,0.003115771,0.00005012968,0.0003812106,0.0001960682,0.00007021397],"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":[0.00001049219,0.00007131346,0.0001702465,0.00004837495,0.00001438778,0.000003301591,0.0002796059,0.09517658,0.00264913,0.008728046,0.0001385906,0.8927099],"study_design_scores_gemma":[0.0002877222,0.0005282986,0.009570909,0.00003405012,0.000003919869,0.000009189514,0.000008518121,0.9625948,0.01084793,0.01597235,0.00001856764,0.0001237679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06506775,0.00001557831,0.9324667,0.0005590587,0.0002594148,0.0004507896,0.000001055443,0.001144888,0.00003470744],"genre_scores_gemma":[0.5399615,1.046333e-7,0.4597254,0.0001578956,0.00004085725,0.00007367288,0.000001334542,0.000005743437,0.00003349378],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8925862,"threshold_uncertainty_score":0.6470959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05236989384220891,"score_gpt":0.360897314909121,"score_spread":0.3085274210669121,"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."}}