{"id":"W2155134093","doi":"10.1186/1476-072x-5-56","title":"An unsupervised classification method for inferring original case locations from low-resolution disease maps.","year":2006,"lang":"en","type":"article","venue":"International Journal of Health Geographics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Geocoding; Health geography; Presentation (obstetrics); Identification (biology); Geographic information system; Health informatics; Computer science; Quality (philosophy); Metadata; Cartography; Geography; Information retrieval; Data science; Public health; Medicine; World Wide Web; Health policy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001129346,0.0001634656,0.0003208648,0.0005864448,0.0001721058,0.00007559951,0.0002706858,0.00006726572,0.00004427294],"category_scores_gemma":[0.0002348795,0.0001580909,0.0002359597,0.0002462854,0.00007093081,0.0004006292,0.00002133078,0.0002553013,0.000005096776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002801697,"about_ca_system_score_gemma":0.0009412121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001413258,"about_ca_topic_score_gemma":0.0003170912,"domain_scores_codex":[0.9975253,0.0002232849,0.001040703,0.0002629262,0.0006958737,0.0002518577],"domain_scores_gemma":[0.9966364,0.0002435357,0.0007750792,0.0003157635,0.001613997,0.0004152342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00461557,0.004331716,0.849459,0.0004880601,0.0009163701,0.002007546,0.0003342933,0.009825159,0.001613423,0.02297285,0.01018175,0.09325428],"study_design_scores_gemma":[0.005176162,0.0004134694,0.8574723,0.0005423227,0.0002487695,0.001020151,0.000286995,0.09371015,0.0000462936,0.008394381,0.03239587,0.0002931156],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4577117,0.001973515,0.5246946,0.01126839,0.001242687,0.0006381799,0.00234218,0.00007979589,0.00004899309],"genre_scores_gemma":[0.9439768,0.0002196435,0.05123964,0.001081455,0.001089236,0.00002750925,0.002326886,0.00002765019,0.00001117584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4862651,"threshold_uncertainty_score":0.6446761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0349796327408408,"score_gpt":0.3930163964248658,"score_spread":0.358036763684025,"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."}}