{"id":"W4416187061","doi":"10.32920/30605294.v1","title":"Generative AI Agents for Travel Behaviour: Applications in Surveys and Modelling","year":2025,"lang":"","type":"article","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generative grammar; Benchmark (surveying); Reliability (semiconductor); Generative model; Human intelligence; Ranging","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003054236,0.0001598166,0.0002922079,0.0002315644,0.00105871,0.000176014,0.0002006373,0.0001722592,0.0002758733],"category_scores_gemma":[0.00004881774,0.0001680804,0.0001219194,0.0009347845,0.0003153546,0.0001546873,0.00002878959,0.0001464516,0.000004130778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001523881,"about_ca_system_score_gemma":0.000409232,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02336198,"about_ca_topic_score_gemma":0.08239558,"domain_scores_codex":[0.9978097,0.000710187,0.0004764224,0.0005334988,0.0001725003,0.0002976723],"domain_scores_gemma":[0.9989074,0.0004681592,0.00007383581,0.0002086067,0.0002420131,0.00009991347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002338316,0.002523967,0.2101114,0.0002972369,0.0003922892,6.319721e-7,0.07410216,0.127753,0.00009668894,0.4905708,0.0008967656,0.09323174],"study_design_scores_gemma":[0.0007136052,0.00003799993,0.03290811,0.00004621062,0.0003032874,1.779649e-8,0.02732315,0.9038479,0.0003324718,0.03266314,0.001447577,0.0003765812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04545093,0.0002524406,0.9477495,0.002241266,0.00004915617,0.001231244,0.00005902208,0.00001285122,0.002953588],"genre_scores_gemma":[0.9878541,0.0002319114,0.0008596308,0.0003203226,0.00005282115,0.0004526376,0.00006737512,0.000006113289,0.01015513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9468899,"threshold_uncertainty_score":0.9831415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05151600339919887,"score_gpt":0.3578446164287833,"score_spread":0.3063286130295845,"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."}}