{"id":"W4408789181","doi":"10.1016/j.commtr.2025.100172","title":"Modular AI agents for transportation surveys and interviews: Advancing engagement, transparency, and cost efficiency","year":2025,"lang":"en","type":"article","venue":"Communications in Transportation Research","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Environment and Climate Change Canada; McGill University; University of Sydney; Concordia University; National Research Foundation Singapore; Singapore-MIT Alliance for Research and Technology Centre; Massachusetts Institute of Technology","keywords":"Transparency (behavior); Modular design; Business; Computer science; Computer security","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":[0.05876978,0.001342666,0.0005131133,0.002620957,0.002448678,0.005366003,0.003140035,0.002495894,0.004523652],"category_scores_gemma":[0.09207703,0.001280155,0.0008364166,0.001236228,0.004950719,0.00822976,0.01479446,0.002339077,0.001977306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002693725,"about_ca_system_score_gemma":0.004832498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001023317,"about_ca_topic_score_gemma":0.002057776,"domain_scores_codex":[0.9121547,0.07681749,0.002090115,0.004317794,0.003485145,0.001134721],"domain_scores_gemma":[0.8746845,0.09438433,0.006827371,0.01636012,0.005128516,0.002615217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008308709,0.001396927,0.01640825,0.001513925,0.0001664279,0.0009230129,0.1826202,0.01816,0.06688713,0.1445107,0.005978179,0.5606043],"study_design_scores_gemma":[0.0008064249,0.001953543,0.01265733,0.001834034,0.0003187637,0.001088826,0.05385121,0.277384,0.04433366,0.2870526,0.3182774,0.0004421104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03485555,0.0001083542,0.9543434,0.001796288,0.00004346784,0.001973743,0.00009162735,0.001375019,0.005412607],"genre_scores_gemma":[0.1470743,0.00008579272,0.8471773,0.0003051648,0.00003695047,0.00366575,0.0001196224,0.0001820345,0.001353165],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05876978,"threshold_uncertainty_score":0.310808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1470134943528009,"score_gpt":0.4417383472024958,"score_spread":0.2947248528496949,"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."}}