{"id":"W4405094850","doi":"10.48550/arxiv.2412.03843","title":"Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metamorphic rock; Test (biology); Computer science; Artificial intelligence; Geology; Paleontology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005684894,0.0004112636,0.0004645936,0.0006205532,0.0004291116,0.000511246,0.001358819,0.0002496219,0.000003430076],"category_scores_gemma":[0.0004007086,0.0004574223,0.00019566,0.0008633958,0.00009749037,0.0002084399,0.002482413,0.0005621869,0.00005414633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007232887,"about_ca_system_score_gemma":0.0008861835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008347879,"about_ca_topic_score_gemma":0.00001412738,"domain_scores_codex":[0.9974163,0.0001836202,0.0002772557,0.001477826,0.0001359003,0.0005091201],"domain_scores_gemma":[0.9969475,0.001127715,0.0001338905,0.001037792,0.0005157358,0.0002373521],"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":[0.00001163025,0.00009280985,0.002226238,0.0003427442,0.0001609342,0.001212049,0.0003429798,0.9427096,0.0003340829,0.04480613,0.007510622,0.0002501599],"study_design_scores_gemma":[0.0001079195,0.0001511603,0.00008780939,0.0005117344,0.00009306243,0.0001120942,0.00002214197,0.9888496,0.0003860933,0.00890803,0.0002326395,0.0005377008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1439593,0.0003269992,0.8484039,0.00008482445,0.0007654215,0.0008974894,0.0001214882,0.005273296,0.0001672224],"genre_scores_gemma":[0.9368472,0.00001554531,0.06166931,0.0000634531,0.000199928,0.0000144125,0.00002341343,0.0000441298,0.001122629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7928879,"threshold_uncertainty_score":0.9997877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2180923605641594,"score_gpt":0.2728530706002629,"score_spread":0.05476071003610347,"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."}}