{"id":"W4390673179","doi":"10.1038/s41597-023-02796-7","title":"Measuring the presence and incidence of cholera in Hindustan: New data from primary sources for the colonial era","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations","funders":"Agence Nationale de la Recherche","keywords":"Harmonization; Cholera; Data collection; Colonialism; Geography; Incidence (geometry); Data science; Regional science; Computer science; Statistics; Mathematics; Biology","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":[0.0007512437,0.0004139935,0.0004134534,0.005043114,0.0005618845,0.0008791068,0.000657575,0.0004693857,0.002441911],"category_scores_gemma":[0.00369058,0.0002283949,0.0003981747,0.006390191,0.0003810721,0.0003028426,0.001278369,0.0005653592,0.001090581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031168,"about_ca_system_score_gemma":0.001487922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08796861,"about_ca_topic_score_gemma":0.1010848,"domain_scores_codex":[0.9991554,0.000217181,0.0000926275,0.0001595872,0.000203237,0.000172017],"domain_scores_gemma":[0.9962941,0.0009138894,0.0009720669,0.0006244886,0.0008572082,0.0003381129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002810969,0.0002426259,0.9249954,0.0006334019,0.0003581923,0.001358297,0.003018725,0.003285203,0.002206492,0.000798233,0.02535906,0.03746315],"study_design_scores_gemma":[0.00002515142,0.00005770163,0.9648022,0.0001057899,0.00007695256,0.0003675104,0.001364356,0.0008642233,0.0008501086,0.0001171497,0.03133972,0.00002906751],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8279194,0.0005928607,0.001082762,0.0003822884,0.00005794842,0.0001200152,0.1667702,0.00006775038,0.003006716],"genre_scores_gemma":[0.6596338,0.0004899058,0.006702896,0.0001592572,0.000107331,0.0003898148,0.3299796,0.00003355509,0.002503916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08796861,"threshold_uncertainty_score":0.1749132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1041119623413403,"score_gpt":0.3332545402285504,"score_spread":0.2291425778872102,"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."}}