{"id":"W2036280319","doi":"10.1088/0026-1394/43/1/013","title":"Pair-difference chi-squared statistics for Key Comparisons","year":2005,"lang":"en","type":"article","venue":"Metrologia","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Statistics; Chi-square test; Key (lock); Mathematics; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007963375,0.0001436096,0.0003023806,0.0002644015,0.000275849,0.000282399,0.0007301928,0.00008025503,0.001306026],"category_scores_gemma":[0.009418057,0.00009988759,0.00009872064,0.0005610724,0.0001229159,0.0001276399,0.00005560014,0.0001035077,0.000615892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008161096,"about_ca_system_score_gemma":0.00008581937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001354678,"about_ca_topic_score_gemma":0.000306355,"domain_scores_codex":[0.9964855,0.0002902557,0.0006425594,0.0005294859,0.001690077,0.0003621365],"domain_scores_gemma":[0.9966874,0.001648636,0.0002810424,0.0005581473,0.0007151621,0.0001095857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001297112,0.0001582854,0.05727439,0.000003181505,0.00002433968,4.258411e-7,0.0003485065,0.001513671,0.002771456,0.01289111,0.7934259,0.1314591],"study_design_scores_gemma":[0.001523251,0.0003676919,0.1935577,0.000005471637,0.00005884951,0.000001183436,0.0003869324,0.4268711,0.00226978,0.02879377,0.3458443,0.0003199969],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1553129,0.0001164786,0.8378757,0.002733541,0.001395885,0.000474599,0.0001526812,0.00007627297,0.001861901],"genre_scores_gemma":[0.901038,0.000001121072,0.09009078,0.0004078132,0.0001618574,0.00004811791,0.00004928593,0.000006639346,0.00819638],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7477849,"threshold_uncertainty_score":0.9996069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4047697023176953,"score_gpt":0.4460307228827394,"score_spread":0.04126102056504405,"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."}}