{"id":"W6904357030","doi":"10.1371/journal.pntd.0009890.s003","title":"QA assessment of STH studies based on modified Newcastle-Ottawa Quality Assessment Scale.","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Quality assessment; Quality (philosophy); Quality assurance; Risk assessment; Evaluation methods","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003960382,0.0002739731,0.00070759,0.0001475934,0.000207217,0.0002015971,0.0007735198,0.0001061678,0.08421524],"category_scores_gemma":[0.01024183,0.0002005654,0.0003474851,0.000771318,0.00003876265,0.0001911916,0.0003133687,0.0002954121,0.0003425768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002717043,"about_ca_system_score_gemma":0.0006688619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001039093,"about_ca_topic_score_gemma":0.00008319355,"domain_scores_codex":[0.9917494,0.001213618,0.001355319,0.0008831925,0.004444979,0.0003535003],"domain_scores_gemma":[0.9921246,0.003325643,0.0006204419,0.001523039,0.002248179,0.0001580623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00006120623,0.00266809,0.02559021,0.0007438012,0.0002338096,0.00005518156,0.0004309612,0.04386069,0.002010861,0.001412077,0.8917677,0.03116544],"study_design_scores_gemma":[0.003143623,0.0008908559,0.7941804,0.003843771,0.00006820368,0.000002503031,0.004881391,0.05076939,0.01074155,0.008178221,0.1222158,0.001084373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2141553,0.00206553,0.004355299,0.02466072,0.003499126,0.00521652,0.3807061,0.0004837404,0.3648576],"genre_scores_gemma":[0.9899416,0.000006584079,0.003361325,0.0009813905,0.00009445558,0.000196167,0.004283136,0.00001473607,0.001120599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7757863,"threshold_uncertainty_score":0.9980953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6275608607273189,"score_gpt":0.538625661623456,"score_spread":0.08893519910386283,"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."}}