{"id":"W4386488973","doi":"10.1162/tacl_a_00595","title":"<b>MIRACL</b>: A Multilingual Retrieval Dataset Covering 18 Diverse Languages","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Relevance (law); Natural language processing; Information retrieval; Process (computing); Quality (philosophy); Artificial intelligence; Resource (disambiguation); World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000502329,0.0001064053,0.0001412832,0.0001366012,0.0003151085,0.00007341236,0.0006532577,0.00008460315,0.000003617879],"category_scores_gemma":[0.002730084,0.00009632376,0.0001213397,0.0006405192,0.00003073275,0.0001005833,0.00006495441,0.0001592435,0.000008110082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535788,"about_ca_system_score_gemma":0.0001412078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001716639,"about_ca_topic_score_gemma":0.000006799247,"domain_scores_codex":[0.9988029,0.00003961305,0.0002858982,0.0002049256,0.0004793269,0.0001873578],"domain_scores_gemma":[0.9979218,0.000817857,0.0003114844,0.0002508848,0.0006646615,0.00003336797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007616745,0.0001995929,0.0007306366,0.0002137484,0.0002373939,0.000005007686,0.001668805,0.8884248,0.001054186,0.08216144,0.02018587,0.005042396],"study_design_scores_gemma":[0.0006211293,0.00004698206,0.0005479318,0.00004597185,0.00006715233,0.00000209255,0.00007361288,0.9226215,0.006450204,0.06412949,0.005160649,0.0002332672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001237391,0.00004949453,0.9942373,0.0003109883,0.0007573956,0.0002972409,0.002458527,0.0004875912,0.0001640916],"genre_scores_gemma":[0.7035652,0.000004043901,0.295231,0.0001034755,0.0001098044,0.00000837638,0.0003518782,0.00001327025,0.0006129894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7023278,"threshold_uncertainty_score":0.3927969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02744140968399567,"score_gpt":0.3310232120994008,"score_spread":0.3035818024154052,"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."}}