{"id":"W4385281006","doi":"10.1016/j.jocm.2023.100431","title":"Theory-driven or data-driven? Modelling ride-sourcing mode choices using integrated choice and latent variable model and multi-task learning deep neural networks","year":2023,"lang":"en","type":"article","venue":"Journal of Choice Modelling","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent variable; Latent variable model; Econometrics; Discrete choice; Econometric model; Pandemic; Task (project management); Mode (computer interface); Preference; Coronavirus disease 2019 (COVID-19); Economics; Marketing; Business; Computer science; Artificial intelligence; Microeconomics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008102601,0.0003607874,0.0005288972,0.0004548276,0.0003707624,0.0002315724,0.0003456099,0.000192669,0.00000729112],"category_scores_gemma":[0.0000957884,0.0003229631,0.0000732126,0.0007534403,0.00006547164,0.001313483,0.00007416221,0.001137515,7.15221e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008638956,"about_ca_system_score_gemma":0.00006437604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001569822,"about_ca_topic_score_gemma":0.0001538905,"domain_scores_codex":[0.9976796,0.00008589987,0.001028195,0.0003788365,0.0003225956,0.0005049014],"domain_scores_gemma":[0.998302,0.0005230452,0.0003408216,0.0002963184,0.0003203712,0.0002174602],"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":[0.00003974622,0.00002913706,0.001931656,0.000101704,0.0001748703,0.000009171778,0.001105971,0.9943098,0.00121159,0.0001164191,0.000005098826,0.0009648225],"study_design_scores_gemma":[0.0009676356,0.00003089228,0.0001076277,0.000240193,0.0002438748,0.00003188834,0.0003222772,0.9974183,0.00001753725,0.0001632413,0.0001190849,0.0003374004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4162713,0.0003768628,0.5828946,0.00001753639,0.0001485494,0.000118306,0.00001824753,0.0001474043,0.000007140473],"genre_scores_gemma":[0.9034418,0.0006939108,0.09539071,0.00004549188,0.000204918,0.000004826581,0.00007694817,0.00009189193,0.00004951816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4875039,"threshold_uncertainty_score":0.9999222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07617742007943569,"score_gpt":0.2935783376492094,"score_spread":0.2174009175697737,"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."}}