{"id":"W3038781317","doi":"10.1093/ije/dyaa087","title":"Recognizing, reporting and reducing the data curation debt of cohort studies","year":2020,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Economic and Social Research Council; Medical Research Council; Department of Health and Aged Care, Australian Government; Canadian Institutes of Health Research; National Institute for Health and Care Research; European Commission; Connected Health Cities; Wellcome Trust","keywords":"Debt; Data curation; Context (archaeology); Technical debt; Data science; Computer science; Business; Finance; Software; Software development; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5418015,0.001023673,0.002336773,0.01000847,0.004899279,0.01732234,0.006977556,0.00827638,0.006765866],"category_scores_gemma":[0.8457506,0.00193801,0.002111071,0.01357306,0.01050492,0.01888292,0.02094489,0.01092135,0.002986838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01269962,"about_ca_system_score_gemma":0.0504105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01415159,"about_ca_topic_score_gemma":0.01154117,"domain_scores_codex":[0.3789999,0.421452,0.1029791,0.01393775,0.07690449,0.005726837],"domain_scores_gemma":[0.07070404,0.6046182,0.1144093,0.10954,0.09379194,0.006936524],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009284554,0.0001462938,0.09291251,0.01594666,0.001038868,0.001995096,0.05829911,0.003367047,0.002799483,0.1478356,0.2089119,0.465819],"study_design_scores_gemma":[0.0001787479,0.0003230076,0.03863047,0.02887928,0.0004336994,0.00220778,0.01010858,0.004747408,0.003159095,0.1269869,0.7839832,0.000361848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.03595085,0.02367895,0.2321493,0.6487907,0.0105716,0.005189885,0.00691434,0.001528538,0.03522583],"genre_scores_gemma":[0.3546453,0.02747092,0.3409303,0.2159665,0.0172113,0.01629346,0.007818866,0.002351705,0.01731166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4581985,"threshold_uncertainty_score":0.5650403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3123556779361549,"score_gpt":0.4488741108666015,"score_spread":0.1365184329304465,"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."}}