{"id":"W7110457758","doi":"10.7910/dvn/qdljcf","title":"Public Data for: Computer Assisted Verbal Autopsy: Comparing Large Language Models to Physicians for Assigning Causes to 6939 Deaths in Sierra Leone from 2019-2022","year":2025,"lang":"","type":"dataset","venue":"Harvard Dataverse","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Sierra leone; Coding (social sciences); Data collection; Public health; Public access; Patient data","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":[0.002759862,0.001405716,0.0009181363,0.002969324,0.0006319046,0.001575812,0.002506515,0.001924062,0.0242462],"category_scores_gemma":[0.01664623,0.0006212021,0.001190521,0.003405511,0.0004658246,0.000983499,0.001875593,0.001778778,0.01732208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001709883,"about_ca_system_score_gemma":0.002744043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06299457,"about_ca_topic_score_gemma":0.08903843,"domain_scores_codex":[0.9987773,0.0003179069,0.0001646952,0.000241454,0.0003252693,0.0001733511],"domain_scores_gemma":[0.9938716,0.002047913,0.0009462267,0.001042915,0.001597548,0.0004938537],"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":[0.0002678453,0.00008249535,0.01160666,0.00069772,0.0001649326,0.00007012402,0.00008467861,0.000747088,0.0001045026,0.0004943112,0.9823117,0.003368011],"study_design_scores_gemma":[0.004143204,0.000202922,0.1510489,0.002364813,0.0003570189,0.0004160311,0.001100691,0.004916422,0.00133375,0.002470088,0.8314737,0.0001723308],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001509281,0.00006501009,0.0000496512,0.0001607809,0.00002613118,0.00001273063,0.9976913,0.0001571087,0.0003281849],"genre_scores_gemma":[0.00278324,0.00003837498,0.0001810963,0.0000416036,0.00001210205,0.00006688632,0.9964609,0.00003230255,0.0003834752],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06299457,"threshold_uncertainty_score":0.1252558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.092697275064366,"score_gpt":0.3183230121442436,"score_spread":0.2256257370798776,"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."}}