{"id":"W4409737882","doi":"10.1371/journal.pgph.0004018","title":"Leveraging deep learning models to increase the representation of nomadic pastoralists in health campaigns and demographic surveillance","year":2025,"lang":"en","type":"article","venue":"PLOS Global Public Health","topic":"Rangeland Management and Livestock Ecology","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth","funders":"Grand Challenges in Global Health; Fogarty International Center","keywords":"Geospatial analysis; Human settlement; Pastoralism; Geography; Robustness (evolution); Data science; Scale (ratio); Computer science; Environmental resource management; Cartography; Archaeology; Forestry","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":[],"consensus_categories":[],"category_scores_codex":[0.001277557,0.00009742362,0.0002330416,0.0001011205,0.000203713,0.00003032812,0.0001845979,0.0000306319,0.0000315174],"category_scores_gemma":[0.0001214504,0.00008176224,0.00002365744,0.001108713,0.0000830878,0.0001742772,0.0002047054,0.0001147218,0.000004167916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003352682,"about_ca_system_score_gemma":0.00007447667,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02017783,"about_ca_topic_score_gemma":0.01717643,"domain_scores_codex":[0.9981328,0.0006169112,0.0003435177,0.00030492,0.0001855701,0.0004162345],"domain_scores_gemma":[0.9993797,0.00009711248,0.0001455388,0.0001840362,0.00001013322,0.0001834877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001362804,0.00008506658,0.9769331,0.00005955026,0.00001155222,8.678016e-7,0.001042749,0.004625862,0.000002761171,0.001985369,0.00104558,0.01419389],"study_design_scores_gemma":[0.000371198,0.0000966311,0.9785711,0.00002455197,0.000001689174,0.000001202519,0.0008715017,0.0158302,2.096868e-7,0.001473489,0.002688189,0.00007000114],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685879,0.0002739593,0.004627291,0.02219229,0.00005110464,0.0006189051,0.000003638259,0.00003066385,0.003614255],"genre_scores_gemma":[0.9969686,0.0001483666,0.0003178432,0.002420132,0.000008885705,0.00003547099,0.000009717146,0.000004017592,0.00008692258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02838076,"threshold_uncertainty_score":0.9863469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03932693518476886,"score_gpt":0.2785222992019057,"score_spread":0.2391953640171368,"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."}}