{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002151855,0.0004024996,0.0004284255,0.001765417,0.0002722558,0.0001913717,0.00110773,0.0001500722,0.001701997],"category_scores_gemma":[0.0003376871,0.0004107707,0.00003841013,0.001393045,0.0007838029,0.0003678914,0.0007461114,0.0004357809,0.00008681172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000431688,"about_ca_system_score_gemma":0.0004677231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002278044,"about_ca_topic_score_gemma":0.006226466,"domain_scores_codex":[0.996693,0.00009292507,0.0003843435,0.001198108,0.0008750922,0.0007565693],"domain_scores_gemma":[0.9984383,0.000142095,0.0002709158,0.0008878697,0.00004429591,0.0002165298],"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":[0.0001765156,0.0005730855,0.0007683012,0.0008300205,0.00008451477,0.0001703734,0.003559477,0.04499222,0.006012262,0.01429774,0.918405,0.01013048],"study_design_scores_gemma":[0.002149726,0.0001781741,0.0001245618,0.0005703611,0.00006935815,0.00004369177,0.001853036,0.6066471,0.0000879534,0.001523766,0.3853676,0.001384608],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.03700697,0.01796778,0.02512572,0.001689834,0.003401243,0.02052488,0.2988569,0.00459129,0.5908353],"genre_scores_gemma":[0.2100205,0.000461027,0.2539187,0.003402631,0.002668303,0.003620346,0.1462602,0.008776309,0.370872],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5616549,"threshold_uncertainty_score":0.9998344,"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."}}