{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03653551,0.0009675947,0.001030398,0.002604068,0.0005894601,0.002122855,0.001462244,0.001243024,0.003091304],"category_scores_gemma":[0.12609,0.0003915478,0.001430439,0.002135298,0.001056891,0.003283256,0.003448278,0.001215966,0.001278962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004924804,"about_ca_system_score_gemma":0.001541482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007984837,"about_ca_topic_score_gemma":0.007323867,"domain_scores_codex":[0.9838213,0.01331864,0.0005055025,0.001024619,0.0007699506,0.0005600957],"domain_scores_gemma":[0.7968032,0.1809177,0.005941396,0.00833503,0.005161226,0.002841398],"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":[0.001013098,0.0001895327,0.8725947,0.0001556074,0.000887006,0.0001422612,0.001211905,0.02496974,0.0002976022,0.002721993,0.002338205,0.09347837],"study_design_scores_gemma":[0.00008551562,0.001513647,0.4351255,0.0002289484,0.0004549696,0.0004466476,0.003933176,0.5392164,0.001383728,0.01402444,0.003481621,0.0001053298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9368647,0.001199898,0.04969609,0.001866897,0.00009426307,0.00009484352,0.00126974,0.0004267476,0.008486846],"genre_scores_gemma":[0.9879975,0.0001180326,0.01050713,0.000111057,0.00006448671,0.00002549931,0.0006099785,0.00003070543,0.0005355446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03653551,"threshold_uncertainty_score":0.1932206,"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."}}