{"id":"W4310155356","doi":"10.1061/jtepbs.teeng-7350","title":"Inferring Trip Destination Purposes for Trip Records Collected through Smartphone Apps","year":2022,"lang":"en","type":"article","venue":"Journal of Transportation Engineering Part A Systems","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hudbay Minerals (Canada); University of Toronto","funders":"","keywords":"TRIPS architecture; Computer science; Global Positioning System; Multinomial logistic regression; Discrete choice; Random forest; Travel behavior; Machine learning; Inference; Gradient boosting; Decision tree; Tree (set theory); Artificial intelligence; Transport engineering; Engineering; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001502559,0.0001378647,0.0003616167,0.0001935721,0.000488326,0.00007247002,0.0002325825,0.00006741167,0.0000601366],"category_scores_gemma":[0.0001322012,0.0001460711,0.0002028123,0.0007181814,0.00002766886,0.0005481316,0.000001873705,0.0002362242,4.932635e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002706578,"about_ca_system_score_gemma":0.0003068141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004233039,"about_ca_topic_score_gemma":0.0004184766,"domain_scores_codex":[0.9978928,0.0000965939,0.0009653096,0.0001576523,0.0006221032,0.0002655566],"domain_scores_gemma":[0.9986662,0.0002173413,0.0005671766,0.00009359625,0.0003544329,0.0001011996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001189692,0.0008312736,0.2420083,0.00133512,0.0005642129,0.0001033233,0.06378019,0.6698238,0.003155882,0.007820687,0.007451475,0.001936092],"study_design_scores_gemma":[0.005276124,0.0007688942,0.187489,0.0004558803,0.0004206772,0.00001688889,0.009095841,0.006746316,0.0006914135,0.0002756239,0.787942,0.0008213262],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9132465,0.0009713609,0.07950962,0.000193782,0.004646295,0.000899875,0.0001210698,0.000117954,0.0002935418],"genre_scores_gemma":[0.9974095,0.00003825604,0.001257882,0.00001274474,0.000530698,0.0001435098,0.00006220842,0.00002362916,0.0005215502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7804905,"threshold_uncertainty_score":0.5956605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03276373654533908,"score_gpt":0.2815161712775741,"score_spread":0.248752434732235,"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."}}