{"id":"W2009759057","doi":"10.1016/j.measurement.2010.03.004","title":"A recommended method for evaluation of international comparison results","year":2010,"lang":"en","type":"article","venue":"Measurement","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Calibration; Gauge (firearms); Block (permutation group theory); Simple (philosophy); Key (lock); Computer science; Mathematics; Engineering drawing; Reliability engineering; Engineering; Algorithm; Statistics; Geography; Computer security; Geometry; Epistemology","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":["metaresearch"],"category_scores_codex":[0.1461073,0.0001195302,0.0002563917,0.0003440502,0.0001252015,0.0001490116,0.0007409733,0.00007345361,0.0009209583],"category_scores_gemma":[0.04069902,0.00009173327,0.0001548185,0.0004045843,0.00003201226,0.0001794242,0.00004748021,0.0001210526,0.00004425463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000167138,"about_ca_system_score_gemma":0.0003095767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002962273,"about_ca_topic_score_gemma":0.0009121919,"domain_scores_codex":[0.9850186,0.0007464307,0.001476898,0.0006180136,0.0119231,0.0002169232],"domain_scores_gemma":[0.9873914,0.000642969,0.0007596604,0.000661062,0.0104676,0.00007728118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005511106,0.0003448511,0.003441843,0.000004516084,0.00007884356,3.759931e-8,0.001235324,0.001783971,0.2283622,0.001295392,0.1260746,0.6368273],"study_design_scores_gemma":[0.006979665,0.0001422449,0.01589041,0.00002585737,0.0001512031,8.67053e-7,0.0008115098,0.6267426,0.1227486,0.03385049,0.1924358,0.0002207447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1890356,0.0001851486,0.6647979,0.0221512,0.03431483,0.005881385,0.0001982993,0.0001120769,0.08332354],"genre_scores_gemma":[0.9624889,4.713063e-7,0.03676642,0.00006443076,0.0001874554,0.0001213571,0.00003679143,0.000006818418,0.0003273617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7734532,"threshold_uncertainty_score":0.9999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6507330414326267,"score_gpt":0.5528794407505461,"score_spread":0.0978536006820806,"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."}}