{"id":"W4408811758","doi":"10.2139/ssrn.5109814","title":"Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation","year":2025,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Armed Forces","funders":"","keywords":"Estimation; Economic geography; Geography; Econometrics; Economics","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":[0.003681795,0.00007329271,0.0001240726,0.0001791283,0.0004562544,0.0001494209,0.0001834524,0.00004692515,0.00001591463],"category_scores_gemma":[0.0001401705,0.00005962371,0.00004778542,0.0004896491,0.0003245762,0.0002928461,0.00002743653,0.0004265708,5.229812e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003953613,"about_ca_system_score_gemma":0.0008991246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008236224,"about_ca_topic_score_gemma":0.01637426,"domain_scores_codex":[0.998326,0.000318501,0.0002788698,0.0001139003,0.0003056455,0.0006570903],"domain_scores_gemma":[0.9995829,0.00009260032,0.0001339947,0.00009951447,0.0000724036,0.00001854809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003561709,0.00002582102,0.07092296,0.00001733698,0.00004143672,0.000001355325,0.005082687,0.0002254877,0.000007679647,0.9091137,0.00004904493,0.01450889],"study_design_scores_gemma":[0.0001942998,0.00001323768,0.1531659,0.00002017427,0.00002747329,0.00000198693,0.02315791,0.0001907928,0.000006265043,0.8224753,0.0006862792,0.00006034801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.91812,0.003175101,0.01230883,0.001573556,0.0004183628,0.0003017191,8.463089e-7,0.00001733476,0.06408419],"genre_scores_gemma":[0.9966403,0.002483226,0.0001394064,0.00007535419,0.0001104511,0.000004703099,0.000001004018,0.000004441555,0.000541067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08663843,"threshold_uncertainty_score":0.9137221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143113426805737,"score_gpt":0.324613283685349,"score_spread":0.3103019410047753,"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."}}