{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001457489,0.0006208313,0.0005051117,0.00167394,0.0002033335,0.0005111327,0.001860626,0.0003082148,0.004019362],"category_scores_gemma":[0.0009626547,0.0005694214,0.00009836613,0.002030996,0.002072278,0.000355473,0.001466432,0.0007718998,0.03758298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004699597,"about_ca_system_score_gemma":0.001073913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008412562,"about_ca_topic_score_gemma":0.001254223,"domain_scores_codex":[0.9949802,0.0000509344,0.0004080159,0.001664428,0.001898817,0.0009976726],"domain_scores_gemma":[0.9977429,0.00006866649,0.0003161671,0.001401927,0.0001062965,0.0003640792],"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":[0.00002743282,0.00007878639,0.00001699649,0.000131846,0.00005080456,0.0004010589,0.0002835525,0.0001374217,0.00680795,0.0002113882,0.9905974,0.001255306],"study_design_scores_gemma":[0.0006203903,0.00007401042,0.000008870553,0.000559961,0.0001668635,0.00006073631,0.001044534,0.0295442,0.001376563,0.0001318933,0.9653652,0.001046822],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.002019368,0.004599833,0.0004075331,0.0001470429,0.004097966,0.001770902,0.152062,0.004785019,0.8301104],"genre_scores_gemma":[0.0179881,0.0001067099,0.02423845,0.0005891639,0.002177884,0.00001425677,0.009302747,0.00314747,0.9424352],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1427592,"threshold_uncertainty_score":0.9996758,"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."}}