{"id":"W4394040045","doi":"10.5281/zenodo.7775521","title":"Bengali Identity Bias Evaluation Dataset (BIBED)","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Migration, Health and Trauma","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bengali; Identity (music); Artificial intelligence; Statistics; Natural language processing; Computer science; Psychology; Mathematics; Art; Aesthetics","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":[0.003757764,0.001761477,0.001192814,0.005222821,0.002735783,0.003038357,0.003924411,0.002259006,0.02487362],"category_scores_gemma":[0.01280255,0.0003971614,0.001068042,0.005875797,0.0009076854,0.002206069,0.003602925,0.00179867,0.04360716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003468697,"about_ca_system_score_gemma":0.002658378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04549823,"about_ca_topic_score_gemma":0.06075494,"domain_scores_codex":[0.9952911,0.001399436,0.0007582718,0.0007943782,0.001305497,0.0004513526],"domain_scores_gemma":[0.9918529,0.001353521,0.0004639105,0.002616365,0.003249379,0.0004637763],"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":[0.0004681279,0.0001542298,0.004389646,0.00148976,0.0001235991,0.0002495592,0.0005358945,0.0006924126,0.00205559,0.002858272,0.9559501,0.03103264],"study_design_scores_gemma":[0.0001664612,0.00007727888,0.01541579,0.0002172227,0.00007581598,0.0002878381,0.0009504291,0.002206421,0.005535525,0.001775829,0.9732126,0.0000788551],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01060595,0.001313811,0.002867312,0.001191587,0.0004819302,0.0005710829,0.959314,0.004322513,0.01933172],"genre_scores_gemma":[0.01133633,0.0002046119,0.003702331,0.0002608562,0.00005038381,0.0005336952,0.9781429,0.0002760248,0.005492912],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04549823,"threshold_uncertainty_score":0.0904668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1805858411253217,"score_gpt":0.3935614777002919,"score_spread":0.2129756365749701,"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."}}