{"id":"W4382983421","doi":"10.1177/03611981231178814","title":"Automatically Refining Degraded and Occluded Lane Marking Information to Enhance the quality of High Definition Maps for Autonomous Vehicles","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Process (computing); Obstacle; Artificial intelligence; Computer vision; Segmentation; Mobile mapping; Kalman filter; Representation (politics); Point cloud; Geography","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":[0.006442639,0.0001691806,0.0003828643,0.0007711106,0.0004795434,0.00006607594,0.000606837,0.0001979203,0.00001780483],"category_scores_gemma":[0.000405413,0.0001234808,0.0001618345,0.001586578,0.0003539631,0.000480766,0.000009794988,0.001098522,0.00001397634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267646,"about_ca_system_score_gemma":0.0001867525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001212879,"about_ca_topic_score_gemma":0.005141181,"domain_scores_codex":[0.9960851,0.000434258,0.001447787,0.0001813832,0.001279981,0.0005715037],"domain_scores_gemma":[0.9960822,0.001965853,0.0002957014,0.0003249637,0.001185579,0.0001456714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007329128,0.0003427606,0.1807188,0.006168783,0.001238298,0.00006046309,0.03019851,0.05363422,0.07557602,0.1774146,0.01265894,0.4546595],"study_design_scores_gemma":[0.0008740994,0.0003633097,0.9672128,0.0002834964,0.00003335446,5.918295e-7,0.001996105,0.001882665,0.006933645,0.01734105,0.002908244,0.000170643],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.986507,0.00006957559,0.007828977,0.004290126,0.0001914449,0.0007379687,0.0001554069,0.0001381551,0.00008134778],"genre_scores_gemma":[0.9931663,0.0003967561,0.006090994,0.00003786162,0.00004113643,0.0001336042,0.00005142503,0.00002932215,0.0000526349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.786494,"threshold_uncertainty_score":0.5035403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07980500846529227,"score_gpt":0.3700623296291033,"score_spread":0.2902573211638111,"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."}}