{"id":"W4405425135","doi":"10.1109/iccvw69036.2025.00176","title":"V-RoAst: Visual Road Assessment Can VLM be a Road Safety Assessor using the iRAP Standard?","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; China Scholarship Council; Chulalongkorn University; UK Research and Innovation; Canadian Thoracic Society","keywords":"Visual inspection; Computer science; Artificial intelligence; Transport engineering; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001320132,0.0005127693,0.00066145,0.0002853079,0.00051164,0.001801984,0.002873505,0.0002767904,0.0001880426],"category_scores_gemma":[0.0001022673,0.0003757024,0.0002780666,0.0008081064,0.0001092988,0.0003165346,0.005674761,0.0008924447,0.000004815015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005322579,"about_ca_system_score_gemma":0.003318185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001531911,"about_ca_topic_score_gemma":0.0007632049,"domain_scores_codex":[0.995981,0.0004212577,0.0009107446,0.001097267,0.001065177,0.0005245919],"domain_scores_gemma":[0.9969484,0.0001175367,0.000477169,0.001820654,0.0004554141,0.0001808357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003768116,0.000792474,0.002111157,0.0005341466,0.001091063,0.00006038809,0.001989616,0.03598745,0.0001147929,0.6169376,0.02396856,0.3163751],"study_design_scores_gemma":[0.0004041165,0.00005343491,0.001273775,0.0001978559,0.00009922993,0.000004757643,0.0003131259,0.961634,0.0001627524,0.001179087,0.03413498,0.0005428618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006961739,0.00006724559,0.9754675,0.005285507,0.001428945,0.0005427402,0.0005039155,0.0003251867,0.01568281],"genre_scores_gemma":[0.5079927,0.0008784333,0.4223274,0.02519314,0.001380143,0.0001777239,0.002381375,0.000174466,0.03949467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9256466,"threshold_uncertainty_score":0.9998695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0509168540457836,"score_gpt":0.404147069356158,"score_spread":0.3532302153103744,"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."}}