{"id":"W6910670859","doi":"10.48448/vdgc-t427","title":"From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multiculturalism; Cultural diversity; Task (project management); Problem of universals; Diversity (politics); Cultural group selection","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":[0.01019365,0.003655678,0.001479711,0.002782976,0.001149829,0.003638985,0.002883467,0.003224382,0.005723519],"category_scores_gemma":[0.02011792,0.0005020691,0.001946824,0.001703012,0.001543959,0.005147253,0.004442059,0.0030997,0.002503095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002203746,"about_ca_system_score_gemma":0.002040163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02695994,"about_ca_topic_score_gemma":0.02834096,"domain_scores_codex":[0.9947866,0.002407202,0.0003578739,0.001486838,0.0006139802,0.0003474385],"domain_scores_gemma":[0.9912857,0.005241753,0.0003724956,0.001643952,0.0008077326,0.0006483475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003229387,0.002323061,0.03237781,0.002984646,0.002740534,0.0008272448,0.001851161,0.2178816,0.009947925,0.005901943,0.04495174,0.6749829],"study_design_scores_gemma":[0.0003155883,0.001635942,0.01137376,0.000605232,0.0005937911,0.0006570873,0.002257594,0.943575,0.01324417,0.01387672,0.01170697,0.0001582033],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8549338,0.02411313,0.06659592,0.003402913,0.001189803,0.0007519539,0.006675651,0.008447479,0.03388943],"genre_scores_gemma":[0.9248621,0.002049245,0.05385556,0.001000354,0.0002223676,0.0001829717,0.01346779,0.0005919232,0.003767522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02695994,"threshold_uncertainty_score":0.05390978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09465074701523643,"score_gpt":0.4157296753615795,"score_spread":0.3210789283463431,"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."}}