{"id":"W2007818470","doi":"10.5555/2662708.2662710","title":"A mutation analysis based benchmarking framework for clone detectors","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"Benchmarking; Benchmark (surveying); Granularity; clone (Java method); Computer science; Detector; Mutation testing; Mutation; Data mining; Software engineering; Operating system; Biology; Genetics; Telecommunications; Business; Gene; Cartography; Geography","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":[0.0002304736,0.00007502374,0.00010661,0.0003481433,0.00006186184,0.0002039668,0.0004032298,0.00005535022,0.0001825781],"category_scores_gemma":[0.0007609251,0.00006739412,0.0001006621,0.00148201,0.00001018825,0.0002374963,0.00005300342,0.0000838037,0.0000403029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004426877,"about_ca_system_score_gemma":0.00002918794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001125819,"about_ca_topic_score_gemma":0.000006362679,"domain_scores_codex":[0.9991201,0.00001921794,0.000120205,0.0002559694,0.0002389331,0.0002455788],"domain_scores_gemma":[0.9973642,0.002010923,0.00002589358,0.0003885009,0.0001296211,0.00008091516],"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":[0.00001519843,0.0002154043,0.1780544,0.0001877306,0.001180804,0.00001980142,0.001256479,0.2156277,0.002843065,0.06255192,0.003301105,0.5347463],"study_design_scores_gemma":[0.00007947382,0.00004203259,0.07004675,0.000005105415,0.00001440966,3.019257e-7,0.000003955285,0.9244682,0.002172567,0.003032197,0.00004174549,0.00009326277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0798284,0.00001171708,0.919275,0.0002729885,0.00009041341,0.0002190815,4.346873e-7,0.0002741642,0.00002784221],"genre_scores_gemma":[0.534691,1.456184e-7,0.4651062,0.00005863036,0.00002547281,0.00008780049,0.000001997973,0.000003851508,0.00002484149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7088405,"threshold_uncertainty_score":0.2748253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01504557180058474,"score_gpt":0.2753145520658611,"score_spread":0.2602689802652763,"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."}}