{"id":"W4406777988","doi":"10.1177/03611981241308873","title":"Estimating Pedestrian Volumes at Intersections using Artificial Intelligence: A ChatGPT Vision Approach","year":2025,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pedestrian; Artificial intelligence; Computer vision; Computer science; Pedestrian detection; Transport 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001028842,0.001155637,0.001338753,0.004224112,0.0006044334,0.001899463,0.001978776,0.001560454,0.001618758],"category_scores_gemma":[0.002125608,0.0007498333,0.00194738,0.002299559,0.0007095048,0.001271538,0.002154784,0.001250594,0.0005649506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070022,"about_ca_system_score_gemma":0.001190335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01226565,"about_ca_topic_score_gemma":0.009332107,"domain_scores_codex":[0.9991098,0.0001880862,0.00003192414,0.0002818232,0.0002409688,0.0001473887],"domain_scores_gemma":[0.9992711,0.0002401041,0.00007917453,0.00008524959,0.0002620549,0.00006223596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002113327,0.0003154348,0.01005008,0.000134005,0.0002208837,0.0003132178,0.0002377098,0.5250309,0.007573148,0.006537863,0.003761728,0.4456136],"study_design_scores_gemma":[0.000004562856,0.0000364015,0.001398894,0.000007634143,0.00001633061,0.00004804531,0.00003146744,0.9950713,0.0007603953,0.002186272,0.0004254434,0.00001324631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04979515,0.0003079492,0.9446122,0.0001815826,0.00008221675,0.00009801385,0.000186034,0.00133986,0.003397017],"genre_scores_gemma":[0.5970986,0.0002805039,0.3985822,0.0002074584,0.0001114214,0.0001768018,0.0008501665,0.00009488693,0.002598078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01226565,"threshold_uncertainty_score":0.02438849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1597383315717902,"score_gpt":0.4659797281778666,"score_spread":0.3062413966060764,"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."}}