{"id":"W4389921041","doi":"10.1080/00401706.2023.2296465","title":"Assessing Measurement System Agreement in the Presence of Reproducibility and Repeatability","year":2023,"lang":"en","type":"article","venue":"Technometrics","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Repeatability; Reproducibility; Replicate; Context (archaeology); Metric (unit); System of measurement; Statistics; Computer science; Measurement uncertainty; Observational error; Accuracy and precision; Mathematics; Engineering; Physics; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.1637087,0.001665385,0.002974866,0.005117721,0.001476003,0.005566957,0.002648236,0.003257671,0.002196271],"category_scores_gemma":[0.4383794,0.001026041,0.003121756,0.005453052,0.004079337,0.004713678,0.006655564,0.002538173,0.0007160641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001846239,"about_ca_system_score_gemma":0.00307119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002995074,"about_ca_topic_score_gemma":0.002302588,"domain_scores_codex":[0.7455838,0.1432322,0.02443594,0.02820213,0.05640168,0.002144201],"domain_scores_gemma":[0.3681023,0.5282611,0.03468141,0.0390434,0.02912893,0.0007829216],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001856863,0.0004894852,0.3445311,0.006530466,0.008456485,0.001262242,0.009699166,0.133926,0.01456109,0.07792602,0.006830992,0.3939302],"study_design_scores_gemma":[0.0002358274,0.002135543,0.2532735,0.001883643,0.002823528,0.001964781,0.003282727,0.4508863,0.02837584,0.2130336,0.04118969,0.0009150242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0715265,0.002260162,0.9173134,0.0004700259,0.0003076427,0.0006401052,0.0008041373,0.0006832361,0.005994717],"genre_scores_gemma":[0.7364203,0.0004627825,0.2589725,0.0003173401,0.0001797975,0.001344791,0.001068827,0.0002832731,0.0009503815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8362913,"threshold_uncertainty_score":0.8657845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.590017664249239,"score_gpt":0.4596789235328383,"score_spread":0.1303387407164007,"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."}}