{"id":"W4385277877","doi":"10.1177/03611981231188370","title":"Winter Road Surface Condition Recognition Using Semantic Segmentation and the Generative Adversarial Network: A Case Study of Iowa, U.S.A.","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Snow removal; Generative adversarial network; Segmentation; Deep learning; Transport engineering; Adversarial system; Hazard; Road surface; Process (computing); Pedestrian; Artificial intelligence; Artificial neural network; Machine learning; Snow; Civil 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":[0.00651166,0.0001921449,0.0003788193,0.000315168,0.000886447,0.0001053541,0.0003403178,0.0001107822,0.0003414576],"category_scores_gemma":[0.0001084966,0.0001317444,0.0001681952,0.001944764,0.001101814,0.0007474745,0.00002094862,0.0007790291,0.00002238579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002116383,"about_ca_system_score_gemma":0.0001112166,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04391218,"about_ca_topic_score_gemma":0.0892977,"domain_scores_codex":[0.9929427,0.002740009,0.00119978,0.000349352,0.002246385,0.0005218056],"domain_scores_gemma":[0.9975508,0.0007315475,0.0006158205,0.0002773707,0.0006805396,0.0001439283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00498108,0.0003275159,0.8613367,0.0001427369,0.0003478606,0.000642664,0.02542862,0.0740035,0.02482038,0.00005508632,0.001757721,0.006156122],"study_design_scores_gemma":[0.007280807,0.0008409965,0.9448466,0.000203684,0.0002410359,0.00003684786,0.0356633,0.005592707,0.00237015,0.002619762,0.00008588759,0.0002182784],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962611,0.00002166745,0.0005259486,0.0005163019,0.0006932528,0.001905957,0.00004149146,0.00001928933,0.0000149721],"genre_scores_gemma":[0.998591,0.0001566036,0.0009322733,0.00001536329,0.0001648421,0.00004452211,0.00002360473,0.00003095456,0.00004083365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08350983,"threshold_uncertainty_score":0.9624545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09143769098250493,"score_gpt":0.3685173888984329,"score_spread":0.277079697915928,"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."}}