{"id":"W7077920206","doi":"10.48448/k2yz-re54","title":"A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology; University of Toronto; McGill University","funders":"","keywords":"Benchmark (surveying); Question answering; Knowledge base; Multiculturalism; Adversarial system; Questions and answers","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":[0.002239234,0.003358421,0.001226464,0.002414718,0.001645983,0.002311122,0.003778735,0.002960991,0.007655971],"category_scores_gemma":[0.009400477,0.0004712361,0.001741905,0.002875865,0.001206995,0.003788179,0.003603295,0.002089696,0.00434973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002659068,"about_ca_system_score_gemma":0.001757737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06819646,"about_ca_topic_score_gemma":0.08120991,"domain_scores_codex":[0.9972045,0.0007949644,0.0001507824,0.001149836,0.0004170087,0.0002829261],"domain_scores_gemma":[0.996811,0.001308693,0.0001274106,0.0008823009,0.0005484442,0.0003222308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001259646,0.001813274,0.01888472,0.003243623,0.0007973421,0.001269808,0.001242192,0.1296461,0.007853556,0.008509794,0.5468588,0.278621],"study_design_scores_gemma":[0.0005911013,0.000838019,0.02331698,0.0006391426,0.00021596,0.001203616,0.003788274,0.6971685,0.01530431,0.03074512,0.2260147,0.0001743575],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5325252,0.02069111,0.06277271,0.006936829,0.001996767,0.00164226,0.2566261,0.05323678,0.06357221],"genre_scores_gemma":[0.3926222,0.001126785,0.08062027,0.001411021,0.000211676,0.0004808346,0.5121202,0.001271907,0.01013508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06819646,"threshold_uncertainty_score":0.1355991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01030860831526746,"score_gpt":0.3008500997751254,"score_spread":0.2905414914598579,"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."}}