{"id":"W2136483635","doi":"10.1002/atr.1306","title":"A new logit‐artificial neural network ensemble for mode choice modeling: a case study for border transport","year":2015,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multinomial logistic regression; Mode choice; Artificial neural network; Mode (computer interface); Computer science; Metropolitan area; Logit; Logistic regression; Discrete choice; Artificial intelligence; Ensemble learning; Econometrics; Machine learning; Operations research; Public transport; Transport engineering; Engineering; Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0007924669,0.0001675828,0.000331868,0.0001186355,0.0003493337,0.00004018527,0.000135413,0.0001114355,0.000006330675],"category_scores_gemma":[0.0001073622,0.0001683562,0.0001950133,0.0003273014,0.00002540037,0.0008379134,3.786063e-7,0.0001457096,2.639271e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006735127,"about_ca_system_score_gemma":0.0005987088,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001117094,"about_ca_topic_score_gemma":0.02452196,"domain_scores_codex":[0.9980416,0.00005385924,0.00089629,0.0002185729,0.0004545671,0.000335074],"domain_scores_gemma":[0.9979157,0.0001753285,0.0004789984,0.0000905976,0.001034589,0.0003047961],"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":[0.001070417,0.0001495148,0.003644025,0.00001493921,0.00004358837,0.00008414641,0.04221786,0.9459166,0.00002343789,0.0005019849,0.0001722286,0.006161284],"study_design_scores_gemma":[0.04755079,0.01055432,0.01582738,0.0003979576,0.003984205,0.0002049263,0.3624696,0.4828586,0.0001719615,0.04054023,0.03266408,0.002775872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4981619,0.00008246157,0.5000331,0.0002961218,0.0006306683,0.0007202561,0.00002215727,0.00003465421,0.00001869282],"genre_scores_gemma":[0.924648,0.00001358455,0.07410273,0.00005944136,0.0008989486,0.00003909641,0.00009110045,0.00002897898,0.0001180942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4630579,"threshold_uncertainty_score":0.993278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07244231297133959,"score_gpt":0.3850144158304051,"score_spread":0.3125721028590655,"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."}}