{"id":"W2557565748","doi":"10.1007/s00216-016-0109-5","title":"Should students be graded on accuracy and precision? Assessment practices in analytical chemical education","year":2016,"lang":"en","type":"article","venue":"Analytical and Bioanalytical Chemistry","topic":"Various Chemistry Research Topics","field":"Chemistry","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medical laboratory; Analytical Chemistry (journal); Accuracy and precision; Computer science; Chromatography; Chemistry; Mathematics; Statistics; Medicine","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006048017,0.0005108569,0.0006568513,0.00009312932,0.0001069961,0.0002979168,0.0006336322,0.0005817576,0.001616097],"category_scores_gemma":[0.006895379,0.0003516466,0.0001636924,0.0003721834,0.000728784,0.0002669714,0.0005748058,0.001005768,0.00001783056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000359885,"about_ca_system_score_gemma":0.0003671373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004320999,"about_ca_topic_score_gemma":0.000005595299,"domain_scores_codex":[0.9956464,0.00005184727,0.0007999481,0.001321265,0.001362871,0.0008177157],"domain_scores_gemma":[0.9953968,0.002471489,0.0002502336,0.0007384581,0.0001761319,0.0009668951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001050263,0.006834633,0.4847727,0.001416586,0.0008078606,0.0003469296,0.00007948861,0.000001008971,0.4366474,0.008876375,0.003723694,0.05544313],"study_design_scores_gemma":[0.01793783,0.0006072246,0.07214648,0.003857357,0.002185404,0.00085558,0.001949349,0.02623991,0.7939554,0.02246619,0.05144471,0.006354616],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9625883,0.000114486,0.00001221812,0.01330254,0.00002148905,0.0001284825,0.00003528338,0.0000679599,0.02372925],"genre_scores_gemma":[0.9919734,0.0003549747,0.0001672268,0.0003941938,0.0003102662,0.00003972185,0.00003655581,0.000035498,0.006688147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4126262,"threshold_uncertainty_score":0.9998935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07671889573212479,"score_gpt":0.4252017536642582,"score_spread":0.3484828579321334,"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."}}