{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001246173,0.001877055,0.0006982739,0.002398933,0.0004727778,0.001653071,0.002170009,0.002110452,0.00843861],"category_scores_gemma":[0.004654747,0.0003572866,0.001021552,0.001109218,0.0006465449,0.003089639,0.002499483,0.001497265,0.008016828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001098652,"about_ca_system_score_gemma":0.00108023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01649451,"about_ca_topic_score_gemma":0.03942508,"domain_scores_codex":[0.998725,0.0002505871,0.00006336994,0.0004750226,0.0002664013,0.0002195277],"domain_scores_gemma":[0.9989625,0.000206012,0.00007473268,0.000366613,0.0002843676,0.0001056669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008583997,0.0004124468,0.01854127,0.002286986,0.0002508874,0.0005641465,0.001124401,0.01983672,0.01772262,0.005532468,0.5846305,0.348239],"study_design_scores_gemma":[0.0002701018,0.0006313864,0.03482877,0.001228286,0.0002570037,0.001495573,0.005300325,0.3802139,0.0603698,0.05487655,0.4602377,0.0002904287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1799597,0.004253379,0.2106507,0.004209775,0.00138971,0.001749955,0.3663836,0.1757671,0.05563615],"genre_scores_gemma":[0.3367399,0.0008141618,0.2001563,0.001350804,0.000196253,0.0006031789,0.4451225,0.003109034,0.01190781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01649451,"threshold_uncertainty_score":0.03279698,"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."}}