{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001849377,0.0005000142,0.000534158,0.0008291865,0.0002520175,0.0002893429,0.001732316,0.0002170254,0.001057866],"category_scores_gemma":[0.0003535762,0.0003223616,0.0001300111,0.002321752,0.003272393,0.0003780457,0.0008096771,0.0005093823,0.002114286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499459,"about_ca_system_score_gemma":0.00069851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004797469,"about_ca_topic_score_gemma":0.00174223,"domain_scores_codex":[0.9951199,0.0002016857,0.0005159229,0.001192033,0.00227348,0.0006969704],"domain_scores_gemma":[0.9978131,0.0003495056,0.0004107321,0.0009445553,0.0002096631,0.0002724543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001887181,0.0002933383,0.000005131529,0.0002696578,0.0005924241,0.0001450519,0.1230308,0.1431258,0.1732402,0.04791437,0.4946308,0.01656365],"study_design_scores_gemma":[0.0005718443,0.0002485453,0.000002065757,0.001806689,0.0002172965,0.000006297538,0.1230483,0.8651627,0.0005540292,0.00571603,0.002054378,0.0006118653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01752547,0.007426131,0.2686125,0.002225227,0.005852342,0.005908826,0.00504524,0.00270011,0.6847042],"genre_scores_gemma":[0.9209227,0.0000080405,0.01435896,0.0001607464,0.0004581791,0.00001198139,0.00007531704,0.0006275639,0.06337654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9033972,"threshold_uncertainty_score":0.9999229,"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."}}