{"id":"W6966742935","doi":"10.48448/4je2-vr88","title":"Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Focus (optics); Task (project management); Baseline (sea); Key (lock)","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":[0.002807067,0.00241872,0.001113361,0.002996746,0.002216579,0.00156684,0.003529161,0.002703806,0.01072602],"category_scores_gemma":[0.007327171,0.0005084889,0.001631124,0.004047459,0.001232167,0.003161423,0.002927383,0.002851392,0.01077635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003750483,"about_ca_system_score_gemma":0.003387202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07216793,"about_ca_topic_score_gemma":0.1006704,"domain_scores_codex":[0.9982055,0.000585904,0.0001611626,0.0005154938,0.0002913131,0.0002405899],"domain_scores_gemma":[0.9971473,0.001130251,0.0001359752,0.0006254963,0.000667288,0.0002937166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0020829,0.002365604,0.0109983,0.003506114,0.0003121278,0.001208546,0.001429019,0.02335785,0.009940345,0.003140172,0.8095707,0.1320883],"study_design_scores_gemma":[0.002489996,0.001883461,0.08001475,0.001349118,0.000460907,0.002372406,0.006025834,0.1679055,0.03199058,0.009408822,0.6956858,0.0004127464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3312735,0.00825789,0.01177345,0.005116162,0.001516709,0.002600195,0.5785015,0.02810007,0.03286057],"genre_scores_gemma":[0.08084468,0.0007161402,0.01772573,0.0005343048,0.0001212419,0.0009313168,0.8909566,0.0004586752,0.007711266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07216793,"threshold_uncertainty_score":0.1434957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01717705669224028,"score_gpt":0.3127035960188599,"score_spread":0.2955265393266196,"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."}}