{"id":"W4407247574","doi":"10.1109/tits.2024.3524117","title":"Predicting Pedestrian Crossing Intentions in Adverse Weather With Self-Attention Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Evacuation and Crowd Dynamics","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Canada Research Chairs","keywords":"Pedestrian; Adverse weather; Computer science; Transport engineering; Engineering; Geography; Meteorology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003280068,0.0009153917,0.0005100204,0.0006148246,0.0002143356,0.0005154524,0.0009842437,0.0006426947,0.0007699908],"category_scores_gemma":[0.0007538171,0.00040211,0.0006357736,0.0003188724,0.0002276134,0.000715851,0.0006107079,0.0009969771,0.0003947101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005153909,"about_ca_system_score_gemma":0.0006162308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01611508,"about_ca_topic_score_gemma":0.02116746,"domain_scores_codex":[0.9998543,0.0000180105,0.000005009986,0.00006200365,0.00002350933,0.00003710686],"domain_scores_gemma":[0.9997647,0.00007481152,0.00003518441,0.00002499976,0.00006958367,0.00003069667],"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":[0.0005824335,0.0005973467,0.02291899,0.00009125225,0.000139131,0.0003415638,0.0001886554,0.7312306,0.01369857,0.001353384,0.006550876,0.2223072],"study_design_scores_gemma":[0.000002847476,0.00002009114,0.00127768,0.0000027824,0.000008301628,0.00001523939,0.000008580143,0.9975631,0.0006544642,0.0003216327,0.0001215941,0.00000358567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6361887,0.001083244,0.3530976,0.0004261633,0.0002731611,0.00008023968,0.0008027906,0.003891351,0.004156579],"genre_scores_gemma":[0.9798571,0.0001686458,0.01737342,0.0000810581,0.00004226641,0.00002015815,0.0007583853,0.00003798356,0.001661035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01611508,"threshold_uncertainty_score":0.03204256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142318802919436,"score_gpt":0.2362169061902235,"score_spread":0.2219850258982799,"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."}}