{"id":"W4408984079","doi":"10.1016/j.latran.2025.100032","title":"Imputing informal workers for transportation modeling in Latin America by the use of machine learning techniques","year":2025,"lang":"en","type":"article","venue":"Latin American Transport Studies","topic":"Taxation and Compliance Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Instituto Tecnológico y de Estudios Superiores de Monterrey; University of Toronto","keywords":"Latin Americans; Computer science; Artificial intelligence; Machine learning; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000999078,0.0005748536,0.0003751215,0.001471646,0.0004720564,0.001269787,0.0005692192,0.0004794722,0.001543226],"category_scores_gemma":[0.002886719,0.0002380732,0.0007864967,0.001308073,0.0002921628,0.0005403517,0.0009503785,0.0005398238,0.0002410229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009735785,"about_ca_system_score_gemma":0.001139836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1202706,"about_ca_topic_score_gemma":0.09464597,"domain_scores_codex":[0.9997246,0.0001341176,0.00001507134,0.0000669258,0.00001821109,0.00004113548],"domain_scores_gemma":[0.9994117,0.0002789168,0.000103514,0.00007281455,0.00009233803,0.00004069658],"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":[0.0001842139,0.0001919992,0.4136707,0.00007984655,0.0002039578,0.0003825147,0.0007332874,0.4985304,0.0007547408,0.005297448,0.002592239,0.07737856],"study_design_scores_gemma":[0.0000107185,0.00001818083,0.02895354,0.00003442674,0.00002355895,0.00002685318,0.0005487286,0.9651667,0.0001020111,0.002941842,0.002160163,0.00001324768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9082095,0.0005614893,0.08476268,0.000886908,0.00005990367,0.00008846065,0.001467682,0.0004945716,0.003468844],"genre_scores_gemma":[0.9780085,0.0002318802,0.01881281,0.00005909729,0.0000355837,0.0000887885,0.001211792,0.00003612135,0.001515356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1202706,"threshold_uncertainty_score":0.239141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06633863661132032,"score_gpt":0.2752550991256667,"score_spread":0.2089164625143464,"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."}}