{"id":"W4410394325","doi":"10.1109/tse.2025.3570897","title":"Using Cooperative Co-Evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Evolutionary algorithm; Artificial intelligence; Distributed computing; Geology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003138952,0.0002769997,0.0002973666,0.0006294523,0.0004813327,0.0002388944,0.0004533585,0.0001036607,0.000002403598],"category_scores_gemma":[0.0003287437,0.0002996254,0.0001104407,0.000913434,0.00002396573,0.0002900104,0.000009353593,0.0002590264,0.00000855636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003618847,"about_ca_system_score_gemma":0.0002425917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001096326,"about_ca_topic_score_gemma":0.000002738718,"domain_scores_codex":[0.998462,0.00004268531,0.0003196897,0.0005291216,0.0002105212,0.0004359915],"domain_scores_gemma":[0.9971633,0.001910972,0.00003582433,0.0004997701,0.0002566666,0.0001334855],"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":[0.000004543202,0.00006588204,0.0001411981,0.00007893083,0.00005314016,0.00001832536,0.0001189886,0.9939077,0.001750977,0.0003473755,0.0007582873,0.002754678],"study_design_scores_gemma":[0.0001861454,0.0001662327,0.000120013,0.0003743316,0.00003069802,0.00009220784,0.000007512775,0.9767396,0.02145765,0.00002382831,0.0004560444,0.0003456857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008792962,0.0001535991,0.9817175,0.00005833947,0.001000222,0.0006137702,0.00005594533,0.007600978,0.00000669474],"genre_scores_gemma":[0.5774199,0.000003092,0.4220361,0.0000688372,0.00004332673,0.0002273734,0.000002041372,0.00002589799,0.0001734407],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5686269,"threshold_uncertainty_score":0.9999456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.047251793029375,"score_gpt":0.3055320633810115,"score_spread":0.2582802703516365,"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."}}