{"id":"W4417086205","doi":"10.48550/arxiv.2505.06107","title":"Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Nationality; Emigration; Country of origin; Proxy (statistics); Immigration; TRACE (psycholinguistics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008202587,0.0002708174,0.000337064,0.0002544916,0.0002787083,0.0001726884,0.0005979849,0.0004575308,0.00001259187],"category_scores_gemma":[0.0003355329,0.0002968047,0.0002057685,0.0004103762,0.00003551556,0.0006519589,0.0004271874,0.0007716093,0.000003534118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101729,"about_ca_system_score_gemma":0.0004134329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001249591,"about_ca_topic_score_gemma":0.0004354595,"domain_scores_codex":[0.9973773,0.0004706686,0.0007227862,0.0007167329,0.0005049227,0.0002075521],"domain_scores_gemma":[0.9976221,0.0002302489,0.0007994748,0.0006983952,0.0005854174,0.00006441766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005685942,0.0001676695,0.7976281,0.0003788216,0.0001620861,0.000001807294,0.001751509,0.1228757,0.067351,0.003910092,0.00001258625,0.005703759],"study_design_scores_gemma":[0.0001876438,0.00001047422,0.07728536,0.0003039048,0.00004057772,2.291819e-7,0.00001934786,0.8015464,0.1122216,0.008164198,0.00000798254,0.0002122335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5010533,0.0001146018,0.4978084,0.0001477563,0.000533123,0.0001748631,0.00005083138,0.0001000711,0.0000170775],"genre_scores_gemma":[0.9720169,0.00001110354,0.02729631,0.0001444539,0.0001116284,0.00002570755,0.000357726,0.000009868315,0.00002628254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7203428,"threshold_uncertainty_score":0.9999484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163688944268923,"score_gpt":0.3189118797857016,"score_spread":0.2025429853588092,"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."}}