{"id":"W3130489108","doi":"10.1016/j.jocm.2023.100451","title":"On-demand transit user preference analysis using hybrid choice models","year":2023,"lang":"en","type":"article","venue":"Journal of Choice Modelling","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Toronto Metropolitan University","keywords":"Latent class model; Preference; Service (business); Computer science; Public transport; Latent variable; TRIPS architecture; Discrete choice; Variable (mathematics); Revealed preference; Mode choice; Latent variable model; Service design; Operations research; Transport engineering; Business; Service provider; Econometrics; Marketing; Statistics; Economics; Engineering; Mathematics; Artificial intelligence; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000311331,0.000154843,0.0003176929,0.0007467002,0.00008366637,0.00005089118,0.0001716564,0.00005806251,0.00003292907],"category_scores_gemma":[0.00001541804,0.000151161,0.0002259271,0.001304712,0.00001624996,0.000484189,0.000003275917,0.0003343416,0.000006214573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006024794,"about_ca_system_score_gemma":0.00003758878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002259261,"about_ca_topic_score_gemma":0.00003075859,"domain_scores_codex":[0.9986213,0.00001884895,0.0006402542,0.0001312755,0.0003626372,0.0002256645],"domain_scores_gemma":[0.9991784,0.000182638,0.0001238177,0.0001771875,0.0002374991,0.0001004509],"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":[0.000008413481,0.00002195133,0.0003166882,0.00003010086,0.0004036998,0.000006292684,0.0003510981,0.9971573,0.00105538,0.0004106633,0.00009315346,0.0001452723],"study_design_scores_gemma":[0.0003353196,0.00001762848,0.0007865997,0.0000576684,0.0004299961,0.000003303604,0.00003338965,0.9958119,0.0007028056,0.001368534,0.0003048145,0.0001480747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4956662,0.00004438744,0.5039082,0.00003014535,0.0001066899,0.00004117754,0.00001358129,0.00006345031,0.0001261294],"genre_scores_gemma":[0.9961036,0.0001184098,0.003513019,0.0000521265,0.0001105185,0.000002286899,0.00001428986,0.00002780098,0.00005792919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5004374,"threshold_uncertainty_score":0.6164166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08803331288135398,"score_gpt":0.2756119974091903,"score_spread":0.1875786845278364,"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."}}