{"id":"W4255420728","doi":"10.1109/icse.2013.6606693","title":"Using mutation analysis for a model-clone detector comparison framework","year":2013,"lang":"en","type":"article","venue":"2013 35th International Conference on Software Engineering (ICSE)","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"clone (Java method); Computer science; Mutation; Precision and recall; Data mining; Artificial intelligence; Genetics; Biology; Gene","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002989449,0.0003501952,0.0004064402,0.0008907095,0.0001095362,0.0005947102,0.001373474,0.0002041301,0.0001725942],"category_scores_gemma":[0.001816793,0.0003720517,0.0002217634,0.0008030605,0.00003074355,0.0007209031,0.0002158238,0.0004689514,0.0001156198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003246804,"about_ca_system_score_gemma":0.0001228593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001277342,"about_ca_topic_score_gemma":0.00000480085,"domain_scores_codex":[0.9974393,0.00002605531,0.0005008004,0.0006637209,0.00082154,0.0005486018],"domain_scores_gemma":[0.9971313,0.000949488,0.0001568466,0.0006580799,0.000869966,0.0002342951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009451573,0.0000609348,0.004433335,0.00003576976,0.0003870201,0.000003630487,0.0003027181,0.9555444,0.0006575176,0.03576378,0.0003060297,0.002495484],"study_design_scores_gemma":[0.0002457487,0.00007009306,0.006036201,0.00008749311,0.00003749576,0.000004411538,0.00001058848,0.9903904,0.0007150213,0.001905684,0.0001074269,0.0003894013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07699851,0.0000439062,0.9207072,0.0002709541,0.0007944276,0.0004462526,0.00003433817,0.0006870994,0.00001730104],"genre_scores_gemma":[0.5554137,0.000005863757,0.444143,0.00004442043,0.00009660408,0.0001552178,0.00002672269,0.00002910479,0.00008546168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4784151,"threshold_uncertainty_score":0.9998732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09241037752275671,"score_gpt":0.3418158109786275,"score_spread":0.2494054334558707,"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."}}