{"id":"W7106850983","doi":"10.48448/ey5n-gv34","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Machine translation; Sentence; Benchmark (surveying); Translation (biology); Repetition (rhetorical device); Training set; Paraphrase","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":[0.001658694,0.001467155,0.0007831085,0.004244397,0.00212013,0.001302182,0.001874507,0.001626688,0.01669221],"category_scores_gemma":[0.008973276,0.0004239886,0.0006991286,0.00423841,0.0007697528,0.002140827,0.002045578,0.0015304,0.01107186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237266,"about_ca_system_score_gemma":0.002601429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01761319,"about_ca_topic_score_gemma":0.02447279,"domain_scores_codex":[0.9986709,0.0004455791,0.0001623066,0.000329252,0.0002660449,0.0001258733],"domain_scores_gemma":[0.9965835,0.001072511,0.0002725327,0.0008479849,0.0009995411,0.0002238364],"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":[0.001544293,0.0006885263,0.01060303,0.004428002,0.0001948915,0.001462444,0.001046992,0.01347814,0.02429952,0.007742506,0.6134431,0.3210685],"study_design_scores_gemma":[0.001001198,0.0005207993,0.0351875,0.000667627,0.0002200724,0.003370229,0.001641865,0.05515335,0.05415053,0.008527129,0.839306,0.0002538449],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1690352,0.005154663,0.04360827,0.002032783,0.001190333,0.001654193,0.7143017,0.02390252,0.0391204],"genre_scores_gemma":[0.1171071,0.000552484,0.04234178,0.0002767199,0.0001263489,0.001094645,0.8318106,0.000956498,0.005733707],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01761319,"threshold_uncertainty_score":0.05584097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05417565129241179,"score_gpt":0.3609821977178405,"score_spread":0.3068065464254287,"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."}}