{"id":"W4403935634","doi":"10.1145/3652620.3687793","title":"Concretize: A Model-Driven Tool for Scenario-Based Autonomous Vehicle Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Systems engineering; Engineering","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":[0.0003569242,0.0001503665,0.0001452939,0.0001083773,0.0001425925,0.0004530918,0.0005602166,0.00006935463,0.000003815916],"category_scores_gemma":[0.0005374676,0.0001313303,0.00008200551,0.0003736693,0.00003666232,0.0002425333,0.000128207,0.0001204857,0.00002336263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007318829,"about_ca_system_score_gemma":0.0003628031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147218,"about_ca_topic_score_gemma":0.000001104188,"domain_scores_codex":[0.9988115,0.00001954039,0.0002119075,0.0004820487,0.000157814,0.0003171277],"domain_scores_gemma":[0.9981242,0.001195782,0.00003262504,0.0004541248,0.0001274409,0.00006587014],"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":[0.00002405376,0.0001224873,0.003850232,0.0005766509,0.00006232782,0.0001334066,0.001043733,0.07541749,0.007951275,0.1889849,0.200006,0.5218275],"study_design_scores_gemma":[0.0001382272,0.0001111653,0.00002886339,0.0001249696,0.00000678313,0.00001040212,4.645122e-7,0.9665638,0.001777979,0.03008684,0.0009485407,0.0002020189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003465064,0.00007129409,0.9593587,0.001070465,0.0001398556,0.0002780277,0.000005210642,0.03464622,0.0009651872],"genre_scores_gemma":[0.417197,1.649058e-7,0.5818635,0.0005598717,0.00003569665,0.0000762474,0.00000180434,0.00001403744,0.0002516089],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8911462,"threshold_uncertainty_score":0.5355493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04396890046626965,"score_gpt":0.2870173616240917,"score_spread":0.2430484611578221,"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."}}