{"id":"W4415947234","doi":"10.1080/15472450.2025.2576883","title":"TransitTalk: Large language model-based digital assistants for enhancing transit customer experience and staff performance","year":2025,"lang":"en","type":"article","venue":"Journal of Intelligent Transportation Systems","topic":"AI in Service Interactions","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Customer experience; Transit (satellite); Public transport; User experience design; Rail transit; Customer relationship management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001660772,0.0006991889,0.0003682138,0.0004216858,0.0005975728,0.001701002,0.001741837,0.000653824,0.01216093],"category_scores_gemma":[0.004912592,0.000424026,0.0005163923,0.0002874945,0.0006300482,0.003598164,0.002964479,0.0009528879,0.003058968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007447514,"about_ca_system_score_gemma":0.001286581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004322851,"about_ca_topic_score_gemma":0.005880943,"domain_scores_codex":[0.9992041,0.0002903417,0.00005491438,0.0002005387,0.0001980415,0.00005202487],"domain_scores_gemma":[0.9980035,0.0009713233,0.0001495021,0.0004423706,0.0002488295,0.0001843437],"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":[0.002806023,0.001208151,0.003804343,0.001076516,0.0001796649,0.0009617459,0.00677603,0.02876831,0.09835589,0.0616452,0.1003716,0.6940466],"study_design_scores_gemma":[0.0005486499,0.001149714,0.00168891,0.000180837,0.0002824999,0.0008989482,0.001799175,0.5710416,0.06969585,0.03734048,0.3151419,0.0002314097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04378055,0.0001758284,0.861457,0.0004351896,0.0001398186,0.0004385048,0.00110467,0.0813223,0.01114615],"genre_scores_gemma":[0.3477398,0.0002171972,0.6219891,0.0003440702,0.000076784,0.0005097579,0.002753579,0.003808581,0.02256112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01216093,"threshold_uncertainty_score":0.04068238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01343871176702882,"score_gpt":0.2864649509613714,"score_spread":0.2730262391943426,"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."}}