{"id":"W3188344990","doi":"10.1155/2021/5513552","title":"The Implications of Weather and Reflectivity Variations on Automatic Traffic Sign Recognition Performance","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Innovates","keywords":"Traffic sign recognition; Sign (mathematics); Traffic sign; Computer science; Cognitive neuroscience of visual object recognition; Variable (mathematics); Warning signs; Warning system; Artificial intelligence; Object (grammar); Engineering; Transport engineering; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0002016696,0.0000891509,0.0001440011,0.00006662049,0.000233387,0.00002770109,0.0001901891,0.00003320455,0.000003783321],"category_scores_gemma":[0.00004942647,0.00007077855,0.00006185575,0.0005475241,0.00004298646,0.0006319157,0.000004167572,0.0001611474,0.000001788333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003649288,"about_ca_system_score_gemma":0.00008756875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.159056e-7,"about_ca_topic_score_gemma":0.00001662818,"domain_scores_codex":[0.9990026,0.00005720977,0.0004761854,0.0001529814,0.0001955279,0.0001155271],"domain_scores_gemma":[0.9982978,0.0004416907,0.000540544,0.0002515624,0.0004178408,0.00005060793],"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":[0.00003152492,0.0001603126,0.0001812723,0.00002614033,0.00003395663,0.000002479368,0.0009375795,0.08568463,0.01683309,0.01263009,0.00003149743,0.8834474],"study_design_scores_gemma":[0.001600125,0.0007340924,0.9033573,0.0002645216,0.0001172892,0.0001211318,0.0002563591,0.02052548,0.02453306,0.04662314,0.00153716,0.0003303611],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6995425,0.0001845184,0.2977292,0.002102472,0.00013154,0.0001671502,0.000007129312,0.000029676,0.000105777],"genre_scores_gemma":[0.9344403,0.0006426889,0.06476884,0.00006191822,0.00003231838,0.00002094606,0.000005408056,0.000007595194,0.00002000045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.903176,"threshold_uncertainty_score":0.2886266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01900445220640407,"score_gpt":0.2727217742057294,"score_spread":0.2537173219993253,"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."}}