{"id":"W7081942663","doi":"10.2139/ssrn.5472828","title":"Misusing I² for Inconsistency, Overlooking OIS for Imprecision, and Ignoring the Continuum of Certainty Ratings: Common Pitfalls in GRADE Assessments","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Sample size determination; Sample (material); Confidence interval; Low Confidence; Test score; Point (geometry)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1735446,0.001356525,0.002759822,0.009753277,0.003497176,0.01232666,0.005676856,0.004572998,0.004208322],"category_scores_gemma":[0.6446171,0.001543252,0.001582209,0.008498556,0.01085257,0.0175082,0.008127841,0.01126863,0.001135803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00304176,"about_ca_system_score_gemma":0.005276534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004303268,"about_ca_topic_score_gemma":0.006255183,"domain_scores_codex":[0.7847351,0.133957,0.02380611,0.0114173,0.04394345,0.00214108],"domain_scores_gemma":[0.3148854,0.5552205,0.03737051,0.0411089,0.04821397,0.003200781],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009355375,0.0001307259,0.02224999,0.002891248,0.0007960536,0.000975502,0.0184286,0.005960128,0.002278271,0.4364901,0.0298483,0.4790156],"study_design_scores_gemma":[0.0001114613,0.000137972,0.007768428,0.001992499,0.000285317,0.00105844,0.004846046,0.0177902,0.00342098,0.9280053,0.03428864,0.0002947555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05838458,0.00516368,0.8218068,0.05506498,0.002295871,0.000807794,0.001007069,0.001594175,0.05387498],"genre_scores_gemma":[0.66201,0.001423547,0.3243535,0.007496238,0.001002221,0.000694111,0.0001990301,0.0004454409,0.002375878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8264554,"threshold_uncertainty_score":0.9178025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01890118179409229,"score_gpt":0.307477860975804,"score_spread":0.2885766791817117,"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."}}