{"id":"W7082249071","doi":"10.48448/f320-g937","title":"AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Economic shortage; Correctness; Benchmark (surveying); Health care; Sophistication; Preference; Healthcare system","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","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001993499,0.0004682202,0.0004956584,0.0006046635,0.0004103495,0.0003522269,0.0055657,0.0004549258,0.001987835],"category_scores_gemma":[0.002048537,0.0004229877,0.00007841418,0.001787277,0.001169157,0.000327375,0.002585005,0.0007011154,0.0002365571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470822,"about_ca_system_score_gemma":0.002539937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008389106,"about_ca_topic_score_gemma":0.00118287,"domain_scores_codex":[0.995306,0.0001028546,0.0005235272,0.001589033,0.001577235,0.0009013903],"domain_scores_gemma":[0.9970924,0.0002040611,0.0003231617,0.001719462,0.0002199939,0.000440968],"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":[0.000003358746,0.0002926909,0.0001683926,0.000169218,0.00004988117,0.0002213937,0.0001594942,0.00006381072,0.0001807376,0.05873435,0.8947583,0.04519835],"study_design_scores_gemma":[0.0003271968,0.00003308275,0.000101424,0.0004286626,0.0000161579,0.0000380664,0.00004910756,0.03804633,0.0002287796,0.001872917,0.9583038,0.0005544788],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000002314363,0.000653531,0.3471788,0.008189015,0.002163015,0.0004073249,0.0004163726,0.0006812154,0.6403084],"genre_scores_gemma":[0.01319162,0.0005311826,0.260998,0.003468662,0.002446095,0.0001187075,0.001818626,0.0001035102,0.7173237],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.0861808,"threshold_uncertainty_score":0.9998222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806332233446785,"score_gpt":0.2990691703336037,"score_spread":0.2810058479991359,"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."}}