{"id":"W6947949615","doi":"10.48448/wbq8-xt62","title":"AraBench: Benchmarking Dialectal Arabic-English Machine Translation","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Unavailability; Suite; Machine translation; Benchmarking; Variation (astronomy); Arabic; Standard English","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","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001874208,0.0004171523,0.0003724707,0.001261077,0.0003533562,0.004244345,0.006995443,0.000153222,0.0004241815],"category_scores_gemma":[0.0008833314,0.0003884758,0.00008508498,0.003131911,0.0006107105,0.01563461,0.001474487,0.0007326235,0.0001571365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001310563,"about_ca_system_score_gemma":0.0006320419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003364692,"about_ca_topic_score_gemma":0.0004589298,"domain_scores_codex":[0.9945584,0.0001790316,0.0004248224,0.001748448,0.002235395,0.0008538906],"domain_scores_gemma":[0.9972185,0.0002404222,0.0004270033,0.001591614,0.0001393282,0.0003831233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000213865,0.000328095,0.0003075394,0.0003374189,0.0001683564,0.0002624775,0.001401453,0.0002015147,0.0009629475,0.2209403,0.1779428,0.5971257],"study_design_scores_gemma":[0.0003360959,0.0001652404,0.00008621967,0.00009764933,0.00002273295,0.000005507687,0.00002942247,0.2147825,0.0000720133,0.0004539829,0.7834004,0.0005482682],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.000003926795,0.0008697956,0.4790536,0.002077786,0.001380787,0.0005816814,0.00004782697,0.000698212,0.5152864],"genre_scores_gemma":[0.04195589,0.005588219,0.7868245,0.002817456,0.006677312,0.0001515079,0.0009507674,0.0008049516,0.1542294],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6054576,"threshold_uncertainty_score":0.9998567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07131721733068196,"score_gpt":0.3264935714448415,"score_spread":0.2551763541141596,"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."}}