{"id":"W4408245171","doi":"10.1136/bmjebm-2024-113077","title":"Rating certainty when the target threshold is the null and the point estimate is close to the null","year":2025,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"Einstein Stiftung Berlin; National Natural Science Foundation of China","keywords":"Certainty; Null hypothesis; Null (SQL); Harm; Confidence interval; Point estimation; Point (geometry); Range (aeronautics); Grading (engineering); Econometrics; Mathematics; Statistics; Computer science; Psychology; Social psychology; Data mining; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2267393,0.00137505,0.003962743,0.008177809,0.001680295,0.009179367,0.002557825,0.007506573,0.007860707],"category_scores_gemma":[0.7258103,0.001230562,0.00438716,0.004398793,0.004692177,0.01032381,0.007836872,0.009955402,0.002289264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003623351,"about_ca_system_score_gemma":0.003633842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002165104,"about_ca_topic_score_gemma":0.002047305,"domain_scores_codex":[0.6835962,0.1847553,0.06761726,0.009912582,0.051911,0.002207627],"domain_scores_gemma":[0.277085,0.5753763,0.04892932,0.03079543,0.06345524,0.004358645],"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":[0.005624315,0.0003396986,0.03868335,0.03934272,0.005685296,0.001135313,0.01560272,0.006934129,0.006433404,0.08204316,0.1011755,0.6970004],"study_design_scores_gemma":[0.003151936,0.003732901,0.04786318,0.06073152,0.008627771,0.006470548,0.0108153,0.03364807,0.01233968,0.5521806,0.2577937,0.002644834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08527002,0.07233574,0.592009,0.1147682,0.01827314,0.006965608,0.004682026,0.002210617,0.1034857],"genre_scores_gemma":[0.6347712,0.01749398,0.3129394,0.01989542,0.004862556,0.004915921,0.001466613,0.0005386097,0.003116299],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7732607,"threshold_uncertainty_score":0.9535681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5544545072542626,"score_gpt":0.533779388139586,"score_spread":0.02067511911467657,"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."}}