{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2232665,0.0005042109,0.002601177,0.0002164196,0.001218216,0.00100396,0.004319274,0.00008785012,0.007346946],"category_scores_gemma":[0.1373863,0.0001154557,0.001013741,0.002073113,0.0009457282,0.0002189394,0.0004759413,0.0005140012,0.0006686706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005274731,"about_ca_system_score_gemma":0.00031509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004395731,"about_ca_topic_score_gemma":0.0001612443,"domain_scores_codex":[0.9746692,0.01107965,0.006529301,0.001218525,0.005974186,0.0005291013],"domain_scores_gemma":[0.9257597,0.0599296,0.003498155,0.009029307,0.001537308,0.0002459388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000124449,0.00001526529,0.00393388,0.00008633265,0.0002127645,0.000006079075,0.008129672,0.0003654196,0.00003326464,0.009124847,0.967621,0.01034704],"study_design_scores_gemma":[0.002129341,0.0002357319,0.005747797,0.004217698,0.002196837,0.00003820795,0.01485491,0.2072164,0.0002951888,0.1286404,0.6339806,0.0004469466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.009351308,0.02171089,0.02977515,0.9280016,0.000651152,0.005321885,0.00001414018,0.0000142868,0.00515957],"genre_scores_gemma":[0.7165158,0.0004154416,0.003598495,0.2558503,0.0009456702,0.00102852,0.000003970436,0.00003017279,0.02161164],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.7071645,"threshold_uncertainty_score":0.9935605,"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."}}