{"id":"W2131375562","doi":"10.1016/s0009-9120(02)00337-5","title":"Proficiency testing performance: a case study with modeling","year":2002,"lang":"en","type":"article","venue":"Clinical Biochemistry","topic":"Pesticide Residue Analysis and Safety","field":"Agricultural and Biological Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; Kingston General Hospital","funders":"","keywords":"Flagging; Statistics; Computer science; 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":[0.0004352886,0.0001334675,0.0002193167,0.000004032272,0.0002625421,0.00004241194,0.0001838649,0.00009149085,0.0001978402],"category_scores_gemma":[0.0002723298,0.00004506723,0.00007868672,0.0003814241,0.00006640775,0.00004983977,0.00006396273,0.0002262379,0.00002537364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001083538,"about_ca_system_score_gemma":0.000007603982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072326,"about_ca_topic_score_gemma":0.00003106654,"domain_scores_codex":[0.9986638,0.00004327945,0.000422426,0.0004284977,0.0001942933,0.000247646],"domain_scores_gemma":[0.999261,0.0002737751,0.00009442701,0.0001133561,0.0001113581,0.0001460802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000265637,0.001317831,0.837819,0.00001660151,0.00004330929,0.001059131,0.00004650406,0.0003130643,0.008910726,4.885155e-7,0.00006612644,0.1503806],"study_design_scores_gemma":[0.001500091,0.005996342,0.09037041,0.0001908684,0.0004085171,0.003253736,0.008644229,0.884901,0.00311065,0.00002392882,0.0001685494,0.001431651],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979032,0.00009942637,0.000005303354,0.0001119383,0.00001549287,0.0001215765,0.000003059257,0.0000576965,0.001682354],"genre_scores_gemma":[0.9993146,0.00001859113,0.0001340228,0.00006846996,0.0002484688,0.00001184448,0.000004283874,9.171258e-7,0.0001988142],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8845879,"threshold_uncertainty_score":0.2166211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1306229440021868,"score_gpt":0.3049046391908572,"score_spread":0.1742816951886704,"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."}}