{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0883948,0.0008482941,0.0006001951,0.001219784,0.004021722,0.003008529,0.003999805,0.002239857,0.001730049],"category_scores_gemma":[0.05780286,0.0004366375,0.000821335,0.00145613,0.002928415,0.001445174,0.004608922,0.001870372,0.000673583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006401956,"about_ca_system_score_gemma":0.0130984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01642977,"about_ca_topic_score_gemma":0.01194732,"domain_scores_codex":[0.9352406,0.04560613,0.002540386,0.003805119,0.009085407,0.003722337],"domain_scores_gemma":[0.9398355,0.02592808,0.003388453,0.008696728,0.01933384,0.002817479],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007071636,0.0210618,0.1327237,0.0008201332,0.0003798137,0.001106143,0.08705256,0.01093805,0.05892919,0.006058022,0.005904835,0.6679541],"study_design_scores_gemma":[0.002765108,0.08936017,0.3909465,0.0007153387,0.0008763645,0.003314121,0.06428467,0.02621598,0.2677188,0.00692768,0.1463682,0.0005069184],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9728074,0.0003923572,0.01782057,0.001214322,0.00004521118,0.001238489,0.00009611913,0.0001754207,0.00621005],"genre_scores_gemma":[0.9780131,0.0001770983,0.01712929,0.0003658628,0.00002149846,0.0002655403,0.0003006574,0.00007382626,0.003653158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9116052,"threshold_uncertainty_score":0.467482,"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."}}