{"id":"W6929385565","doi":"10.48448/ab17-pa36","title":"MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages","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 Waterloo","funders":"","keywords":"Annotation; Relevance (law); Process (computing); Multilingualism; Resource (disambiguation); Heuristic","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":[0.00238592,0.002666784,0.001575664,0.009139653,0.002074912,0.003168228,0.002642267,0.002548339,0.02369721],"category_scores_gemma":[0.0092996,0.0006640662,0.001312633,0.006298566,0.0008140256,0.003661064,0.003680848,0.001720175,0.05243802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00180148,"about_ca_system_score_gemma":0.00238659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02227138,"about_ca_topic_score_gemma":0.0457303,"domain_scores_codex":[0.9963648,0.0007849569,0.0006702676,0.0008602291,0.001003471,0.0003163591],"domain_scores_gemma":[0.9960991,0.0009447159,0.0002862625,0.0006827512,0.001528098,0.0004589953],"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":[0.0003422467,0.0001673714,0.003243231,0.002984747,0.0001242018,0.0003853767,0.0004760249,0.0007302248,0.005843657,0.00142574,0.9539832,0.03029399],"study_design_scores_gemma":[0.0003646033,0.0001824764,0.01209925,0.0004050107,0.0001325521,0.001045063,0.001100839,0.005615319,0.006544972,0.001819163,0.9704827,0.0002081237],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01540125,0.00241664,0.004560034,0.0005432973,0.0002998239,0.0004405287,0.9495471,0.01153593,0.01525539],"genre_scores_gemma":[0.00677639,0.0001800546,0.005884236,0.0001405173,0.00003219003,0.0002482494,0.9835872,0.0004012216,0.002750001],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02369721,"threshold_uncertainty_score":0.07927513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04902513819283109,"score_gpt":0.3796876105270611,"score_spread":0.33066247233423,"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."}}