{"id":"W2053264768","doi":"10.1145/1370256.1370279","title":"Towards a mutation-based automatic framework for evaluating code clone detection tools","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; clone (Java method); Cloning (programming); Code (set theory); Mutation; Frame (networking); Software engineering; Data mining; Machine learning; Programming language","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":[0.0005975376,0.0001030722,0.0001217735,0.000138931,0.0001947409,0.0001209685,0.0004137614,0.00007570604,0.0000310475],"category_scores_gemma":[0.006959641,0.00009860763,0.00006375842,0.0005296962,0.00002401267,0.0002795656,0.00005109717,0.0001398278,0.00004075741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001198507,"about_ca_system_score_gemma":0.0002404684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002090338,"about_ca_topic_score_gemma":0.000002865917,"domain_scores_codex":[0.9986765,0.00004527596,0.000202515,0.000283177,0.0005053893,0.0002870748],"domain_scores_gemma":[0.996058,0.003205251,0.00004450637,0.0004030275,0.0002100983,0.00007913526],"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":[0.00001967643,0.0001306931,0.001287258,0.0002310295,0.00005141701,0.00003487475,0.001551518,0.06724204,0.003062554,0.008717063,0.0003728015,0.9172991],"study_design_scores_gemma":[0.0003104878,0.0002004699,0.0118443,0.00002863425,0.000002813271,0.00001882702,0.000006457687,0.9662572,0.01778781,0.003389052,0.00002877448,0.0001251876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1685681,0.00001732121,0.8296944,0.0002655796,0.0002129138,0.0003767211,0.000001598002,0.0008331658,0.00003016195],"genre_scores_gemma":[0.5105053,3.246572e-7,0.4892027,0.00007531514,0.00003038665,0.0001471903,0.000001336298,0.000008483988,0.00002890206],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9171739,"threshold_uncertainty_score":0.8331843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08639718895178901,"score_gpt":0.3610098544698568,"score_spread":0.2746126655180678,"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."}}