{"id":"W2896425003","doi":"10.1016/j.tbs.2018.09.008","title":"Estimating a Toronto pedestrian route choice model using smartphone GPS data","year":2018,"lang":"en","type":"article","venue":"Travel Behaviour and Society","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":76,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pedestrian; Global Positioning System; Transport engineering; Mixed logit; Revealed preference; Computer science; Discrete choice; Logit; Travel behavior; Geography; Logistic regression; Engineering; Mathematics; Econometrics; Telecommunications; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000394318,0.0006841534,0.0005468034,0.0008449639,0.0006038262,0.000897344,0.0009485372,0.0009483349,0.002943619],"category_scores_gemma":[0.001498658,0.0008422972,0.0009733365,0.00141619,0.0003927356,0.000652439,0.0004792831,0.0007511109,0.0006524408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00336089,"about_ca_system_score_gemma":0.002692613,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6155071,"about_ca_topic_score_gemma":0.6172949,"domain_scores_codex":[0.9998059,0.00003990256,0.000007728651,0.00007867812,0.00002457367,0.00004326466],"domain_scores_gemma":[0.9995596,0.0002369557,0.00004086654,0.00003674074,0.00008304787,0.00004276699],"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":[0.0001882804,0.00008520004,0.03628423,0.00003938342,0.0001077254,0.0001281892,0.0001123887,0.9459746,0.0007264948,0.001494606,0.001948822,0.01291],"study_design_scores_gemma":[0.00001201598,0.00002324605,0.008255923,0.000005090983,0.00002237468,0.00001428726,0.00003757385,0.9909528,0.00009847396,0.0003104754,0.0002582163,0.000009387428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9560338,0.0003604171,0.03736899,0.0003845782,0.00004455375,0.00004142882,0.003491249,0.0003349198,0.001940113],"genre_scores_gemma":[0.9884135,0.0001506024,0.006617323,0.00001777913,0.00001735372,0.00002935077,0.00215912,0.00001404729,0.002581045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3844929,"threshold_uncertainty_score":0.7735146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1166961640146181,"score_gpt":0.3806570571560214,"score_spread":0.2639608931414034,"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."}}