{"id":"W2806282111","doi":"10.1002/stvr.1669","title":"MuMonDE: A framework for evaluating model clone detectors using model mutation analysis","year":2018,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"clone (Java method); Preprocessor; Mutation; Computer science; Mutation testing; Data mining; Detector; Precision and recall; Software engineering; Artificial intelligence; Genetics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001894408,0.0001848413,0.0002376226,0.0002470752,0.0004810793,0.0001702951,0.0004145512,0.0001566119,0.000001839753],"category_scores_gemma":[0.0294845,0.0001849019,0.00009184403,0.001735409,0.0001550966,0.0003381261,0.0001381276,0.0002145131,0.000002508162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001778609,"about_ca_system_score_gemma":0.0002364366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004814708,"about_ca_topic_score_gemma":0.000001723217,"domain_scores_codex":[0.9979345,0.00008509376,0.0003996741,0.0008015328,0.0004218349,0.0003573792],"domain_scores_gemma":[0.9948491,0.002770693,0.0001831385,0.000939868,0.001110206,0.0001469438],"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":[0.00001733581,0.00005473328,0.02515528,0.0001069596,0.00004430519,3.134092e-7,0.001149725,0.9471109,0.002028612,0.0009891633,0.00001058552,0.02333208],"study_design_scores_gemma":[0.0001469682,0.00008464389,0.01149756,0.00002938034,0.00007682997,0.000002348462,0.0000105422,0.9474027,0.0005640456,0.03998723,0.000001082486,0.0001966872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3954381,0.00002227311,0.6036503,0.00004463151,0.00006049246,0.0002779367,0.000007986967,0.000495792,0.000002521333],"genre_scores_gemma":[0.4895285,6.732877e-7,0.5103564,0.00002122538,0.00002748511,0.00004111289,0.000005690792,0.00001132039,0.000007650186],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09409037,"threshold_uncertainty_score":0.9786906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031035430604409,"score_gpt":0.3755641998763948,"score_spread":0.2724606568159539,"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."}}