{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001534584,0.001189108,0.0005119028,0.00144299,0.0003777522,0.000663567,0.001797328,0.0011278,0.001526961],"category_scores_gemma":[0.007783405,0.0004198828,0.0006922236,0.0005084518,0.001005273,0.0007663294,0.001284452,0.0009002862,0.0001962421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00087293,"about_ca_system_score_gemma":0.001307267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006375893,"about_ca_topic_score_gemma":0.008273046,"domain_scores_codex":[0.9989517,0.0004176127,0.00004882375,0.0001669955,0.0002883791,0.0001263969],"domain_scores_gemma":[0.9949949,0.003676918,0.0002698369,0.0003539529,0.0005290476,0.0001753427],"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":[0.00009851458,0.0001818235,0.006236514,0.00008341988,0.00005321792,0.0002861899,0.0001050483,0.9251176,0.004838897,0.003061344,0.0008787625,0.05905876],"study_design_scores_gemma":[0.00001477614,0.00004945814,0.0002129112,0.000005483356,0.000007133104,0.00002171369,0.0000168016,0.9970073,0.001049109,0.00132403,0.0002879724,0.000003318366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5044192,0.0006381714,0.4836603,0.0006519328,0.0000934637,0.0003598626,0.000248249,0.002954812,0.006973918],"genre_scores_gemma":[0.8796749,0.00007823899,0.118275,0.0001593779,0.00001200065,0.0001750455,0.0003562571,0.000147416,0.001121763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006375893,"threshold_uncertainty_score":0.01267755,"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."}}