{"id":"W4289792821","doi":"10.1109/tiv.2022.3196396","title":"Verification and Validation Methods for Decision-Making and Planning of Automated Vehicles: A Review","year":2022,"lang":"en","type":"review","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Systems engineering; Hierarchy; Range (aeronautics); Reliability 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007802529,0.0003561676,0.001042195,0.0003878206,0.0002196046,0.00001982883,0.000204423,0.0003278172,0.00005830862],"category_scores_gemma":[0.00007146779,0.0003519997,0.0002390705,0.0003499218,0.00008968839,0.00007713048,0.000005139974,0.0005010397,0.000003578434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371902,"about_ca_system_score_gemma":0.00004677259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001997515,"about_ca_topic_score_gemma":6.331014e-7,"domain_scores_codex":[0.9982271,0.0001725898,0.0008861354,0.0003874779,0.0001198033,0.0002068978],"domain_scores_gemma":[0.9971547,0.002175431,0.0002346373,0.0003439267,0.0000431494,0.00004813202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001396554,0.00002812972,2.220846e-7,0.01579836,0.0001828692,7.8635e-7,0.00009818932,0.002275187,0.0000118508,0.00004273986,0.00006554343,0.9814821],"study_design_scores_gemma":[0.0001880913,0.0002395889,0.000003244541,0.05945416,0.002118841,0.00009313659,0.0001588082,0.07538985,0.001830143,0.0005603418,0.8591122,0.0008515907],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000348359,0.5726779,0.4258933,0.00000505481,0.0001872,0.0006992207,0.00006088892,0.0004249327,0.00001666622],"genre_scores_gemma":[0.00155723,0.9771098,0.02061748,0.00001757894,0.00001348605,0.0005781038,0.00002099524,0.00007618123,0.000009093554],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9806306,"threshold_uncertainty_score":0.9998932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06416434948146378,"score_gpt":0.3921944433084235,"score_spread":0.3280300938269597,"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."}}