{"id":"W2092953325","doi":"10.1007/s00769-014-1049-4","title":"Harmonization and transferability of performance assessment: experience from four serum aluminum proficiency testing schemes","year":2014,"lang":"en","type":"article","venue":"Accreditation and Quality Assurance","topic":"Pesticide Residue Analysis and Safety","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de Santé Publique du Québec","funders":"","keywords":"Harmonization; Standard deviation; Transferability; Computer science; Statistics; Reliability engineering; Mathematics; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006840214,0.00009638051,0.0002074316,0.000008775947,0.0001972263,0.00004139112,0.00008860238,0.00005234243,0.00002957951],"category_scores_gemma":[0.0004982656,0.00004751166,0.00002664367,0.0002525834,0.0001075533,0.0003247607,0.00002003353,0.0000658288,5.833051e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006815407,"about_ca_system_score_gemma":0.00001082028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002895623,"about_ca_topic_score_gemma":0.0001571664,"domain_scores_codex":[0.9988434,0.0001888566,0.0003433957,0.0002762656,0.0002215153,0.0001266228],"domain_scores_gemma":[0.9987531,0.0008132897,0.0001480855,0.00005847052,0.000171758,0.00005529684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009538206,0.00002724303,0.7874461,0.00003349844,0.00000533129,6.19653e-8,0.0002695072,0.00001811553,0.1111872,0.0005179799,0.00000187962,0.1004836],"study_design_scores_gemma":[0.0001269924,0.00008164254,0.9830018,0.00003184998,0.00001034328,4.178994e-7,0.0003141359,0.01006286,0.005750215,0.0003337876,0.0001803409,0.0001056065],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956561,0.00007999087,0.00326457,0.0005387409,0.00003177209,0.00009958057,0.00003432825,0.00002345995,0.0002714865],"genre_scores_gemma":[0.9978876,0.00008409515,0.001840914,0.00007088882,0.00006324115,0.00001014372,0.00003174633,6.583954e-7,0.00001075222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1955557,"threshold_uncertainty_score":0.1937469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06021817124645472,"score_gpt":0.288018029644113,"score_spread":0.2277998583976583,"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."}}