{"id":"W3197386932","doi":"10.1007/s11116-021-10228-x","title":"A hybrid data fusion methodology for household travel surveys to reduce proxy biases and under-representation of specific sub-group of population","year":2021,"lang":"en","type":"article","venue":"Transportation","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Proxy (statistics); Travel survey; Travel behavior; Survey data collection; Geography; Population; Descriptive statistics; Survey methodology; Computer science; Econometrics; Economics; Statistics; Transport engineering; Demography; Sociology; Engineering; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00149566,0.00008521847,0.000259297,0.0000795505,0.000107392,0.00001354892,0.000136253,0.00006468742,0.00002694064],"category_scores_gemma":[0.0001513971,0.0000921853,0.00005121508,0.000296557,0.0000946383,0.0003483834,0.000004276312,0.0000422434,1.485034e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001543685,"about_ca_system_score_gemma":0.0000548785,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005079275,"about_ca_topic_score_gemma":0.01987924,"domain_scores_codex":[0.998459,0.0003131308,0.0004657577,0.0003820233,0.0002463003,0.0001337443],"domain_scores_gemma":[0.9988614,0.0004439515,0.0001984236,0.0002663574,0.0001707005,0.00005917129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004141172,0.0003664571,0.6311539,0.0002915796,0.00004875604,0.000004178,0.007017761,0.0004294596,0.3076359,0.01016467,0.00009478341,0.04237835],"study_design_scores_gemma":[0.0003822065,0.00004442375,0.9220927,0.00003849994,0.00005717194,1.290967e-7,0.001197873,0.00004517292,0.07266938,0.003335682,0.00004830839,0.0000884687],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9102773,0.000121098,0.08785961,0.0002603083,0.0001240408,0.0005444615,0.0007649919,0.00002028199,0.00002793199],"genre_scores_gemma":[0.9861116,0.0001200213,0.009229327,0.00001285464,0.00005061043,0.00001291254,0.004426458,0.0000110469,0.0000251361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2909387,"threshold_uncertainty_score":0.9980054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3288126151386405,"score_gpt":0.4111024442606248,"score_spread":0.08228982912198429,"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."}}