{"id":"W4406489459","doi":"10.1017/pan.2024.24","title":"Decoupling Visualization and Testing when Presenting Confidence Intervals","year":2025,"lang":"en","type":"article","venue":"Political Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Decoupling (probability); Confidence interval; Computer science; Visualization; Reliability engineering; Statistics; Data mining; Mathematics; Engineering; Control engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002167237,0.0001411702,0.0006469056,0.0002476107,0.0001158039,0.0001239979,0.0001646143,0.0001047992,0.0002020713],"category_scores_gemma":[0.2541289,0.0001241918,0.0001566925,0.0008874477,0.0001889673,0.00006303472,0.0002173599,0.0001532159,0.00000620167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004029766,"about_ca_system_score_gemma":0.00003120924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000134722,"about_ca_topic_score_gemma":0.00001472093,"domain_scores_codex":[0.997662,0.0004138564,0.0008906416,0.0003915915,0.0002364687,0.0004054372],"domain_scores_gemma":[0.9284964,0.07061142,0.0001494904,0.0003021077,0.0002565908,0.0001840229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004913936,0.0000433122,0.04191287,0.0001258127,0.0004682963,0.000002707588,0.00004490787,0.000003892123,0.00004317728,0.9557829,0.00005718151,0.001510065],"study_design_scores_gemma":[0.000140415,0.00001165494,0.005199994,0.00009334669,0.001976062,6.168985e-7,0.000086017,0.101655,0.000711078,0.8900033,0.00001581101,0.0001067175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.069282,0.00002728888,0.9236815,0.00054485,0.00007654146,0.0001406894,0.00001130273,0.00009953957,0.006136298],"genre_scores_gemma":[0.6362359,0.000001735989,0.3630662,0.0003240434,0.00007067183,0.00001213891,0.000001050815,0.000008544219,0.0002797348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5669539,"threshold_uncertainty_score":0.7521539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5242550988197755,"score_gpt":0.599761551093115,"score_spread":0.07550645227333952,"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."}}