{"id":"W3120385278","doi":"10.1109/iv47402.2020.9304698","title":"A Unified Evaluation Framework for Autonomous Driving Vehicles","year":2020,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Reliability (semiconductor); Software deployment; Fidelity; Automation; Safety assurance; Scenario testing; Reliability engineering; Track (disk drive); Test (biology); Engineering; Software engineering; Telecommunications; Artificial intelligence; Variety (cybernetics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03320158,0.002240439,0.001357434,0.006046049,0.001297619,0.007480967,0.004638514,0.002553514,0.004115609],"category_scores_gemma":[0.03129597,0.001095259,0.002692641,0.001894024,0.002549351,0.006908021,0.006547414,0.003212562,0.002287488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003194154,"about_ca_system_score_gemma":0.008360461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027078,"about_ca_topic_score_gemma":0.009031868,"domain_scores_codex":[0.9739895,0.009890983,0.003575195,0.002182976,0.00920637,0.001155009],"domain_scores_gemma":[0.979018,0.005622276,0.001352942,0.003430261,0.009617241,0.0009593171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001934714,0.0005230779,0.005610603,0.001404314,0.0003561254,0.000843757,0.00178567,0.09272455,0.01079987,0.5899364,0.01711802,0.2787041],"study_design_scores_gemma":[0.000104303,0.0003767777,0.001922742,0.001244708,0.0002498701,0.000696976,0.0007857089,0.5724117,0.01198481,0.2779257,0.1320965,0.0002004092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001476622,0.0002699597,0.9899607,0.0003626994,0.00005103856,0.000646285,0.0002263079,0.003325975,0.003680335],"genre_scores_gemma":[0.05890016,0.0003810932,0.935247,0.0002056783,0.00009180203,0.001114489,0.001210566,0.0008817657,0.00196745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03320158,"threshold_uncertainty_score":0.1755888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02838895735510281,"score_gpt":0.2586327546624692,"score_spread":0.2302437973073663,"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."}}