{"id":"W4389284528","doi":"10.1016/j.jocm.2023.100454","title":"Ordinal-ResLogit: Interpretable deep residual neural networks for ordered choices","year":2023,"lang":"en","type":"article","venue":"Journal of Choice Modelling","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Ordinal regression; Ordinal data; Computer science; Residual; Logit; Consistency (knowledge bases); Artificial intelligence; Artificial neural network; Ordered logit; Statistics; Econometrics; Machine learning; Mathematics; Algorithm","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":[0.001272436,0.0009090842,0.0007881885,0.0004702927,0.000261923,0.0009497576,0.002017804,0.00166104,0.01124232],"category_scores_gemma":[0.006078058,0.0005903775,0.0008860801,0.00052803,0.0004905386,0.001821943,0.001639193,0.002823456,0.002516204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009493636,"about_ca_system_score_gemma":0.0008371486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007960549,"about_ca_topic_score_gemma":0.01661127,"domain_scores_codex":[0.9996967,0.0001234467,0.00001852743,0.00007143868,0.0000493277,0.00004054298],"domain_scores_gemma":[0.9989247,0.0006876884,0.00005752354,0.0001589932,0.0001185268,0.0000526333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005044932,0.0002700334,0.001841735,0.0002756552,0.0001542039,0.0001586401,0.0001168574,0.5910134,0.002026587,0.03800054,0.02099201,0.3446458],"study_design_scores_gemma":[0.00001186745,0.00001564882,0.00006715591,0.00001216847,0.000005086572,0.00000491269,0.000004444925,0.9846376,0.0002762801,0.01439047,0.0005697286,0.000004601953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04583657,0.001192949,0.9345215,0.0009942668,0.000288456,0.0001116039,0.003097671,0.009865018,0.004091906],"genre_scores_gemma":[0.6312908,0.0006858208,0.3451221,0.0007333181,0.000135771,0.0003741581,0.005189489,0.001133949,0.01533462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01124232,"threshold_uncertainty_score":0.03760934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.14154998753376,"score_gpt":0.2570540448490615,"score_spread":0.1155040573153015,"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."}}