{"id":"W6950465891","doi":"10.5683/sp3/42vz4p","title":"MaRVL: Multicultural Reasoning over Vision and Language","year":2021,"lang":"en","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Task (project management); Selection (genetic algorithm); Statement (logic); Hierarchy; Mandarin Chinese; Multiculturalism; First language","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":[0.001195049,0.005743345,0.001548517,0.003773468,0.001654657,0.003805234,0.004721568,0.003083803,0.05612579],"category_scores_gemma":[0.006462283,0.0009716345,0.002264017,0.00335621,0.0007841132,0.004686215,0.003849429,0.003128048,0.04499967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00269127,"about_ca_system_score_gemma":0.001861728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03940367,"about_ca_topic_score_gemma":0.08006402,"domain_scores_codex":[0.9980521,0.0003825656,0.0001490233,0.000816259,0.0004184644,0.0001815887],"domain_scores_gemma":[0.9976702,0.0008919943,0.0001217606,0.000714934,0.0003832873,0.0002177151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003364765,0.0002019842,0.0022034,0.001593444,0.000118021,0.0002333549,0.000232279,0.001609734,0.001198954,0.002842507,0.9506528,0.03877701],"study_design_scores_gemma":[0.0004694134,0.0001653819,0.01095268,0.000890429,0.0001514203,0.0007845716,0.001052687,0.01728282,0.005327621,0.01494374,0.9478348,0.0001443509],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006361812,0.001638519,0.004874806,0.0004856588,0.0002124183,0.0002049339,0.9567624,0.01399445,0.0154649],"genre_scores_gemma":[0.006906235,0.0001967398,0.005284603,0.0001216258,0.00001580255,0.0002013741,0.9848423,0.0003418826,0.002089468],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05612579,"threshold_uncertainty_score":0.1877595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008741012504971028,"score_gpt":0.2908463182556846,"score_spread":0.2821053057507136,"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."}}