{"id":"W4414223511","doi":"10.1080/08982112.2025.2550316","title":"Assessing counting systems using a gold standard or a true count","year":2025,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Gold standard (test); Standard deviation; Range (aeronautics); Statistical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.06037726,0.00220135,0.002731797,0.008645179,0.001801342,0.01195202,0.006235477,0.0052077,0.002874481],"category_scores_gemma":[0.1693112,0.00100394,0.002065028,0.003918442,0.007627243,0.01267149,0.005868645,0.003847075,0.001496477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005911215,"about_ca_system_score_gemma":0.005437039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006923731,"about_ca_topic_score_gemma":0.006114196,"domain_scores_codex":[0.9158142,0.03410755,0.00517305,0.0151604,0.02780554,0.001939225],"domain_scores_gemma":[0.8473727,0.09173948,0.0201921,0.01448627,0.02425975,0.001949717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004606076,0.0005093462,0.09531145,0.001180415,0.0007862421,0.0004866588,0.003177931,0.1117518,0.004227944,0.4988596,0.0110612,0.2721868],"study_design_scores_gemma":[0.00009688378,0.0009074067,0.01968106,0.0006299663,0.0002723173,0.0007286338,0.001243192,0.5103422,0.00576738,0.4456564,0.01427274,0.0004019143],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0161984,0.0005941595,0.9720233,0.003786522,0.0001662686,0.0002460723,0.0003262666,0.0005385319,0.006120356],"genre_scores_gemma":[0.4392629,0.0004974623,0.5544043,0.001051246,0.0002291929,0.0007713008,0.0005051758,0.0001290304,0.003149442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06037726,"threshold_uncertainty_score":0.3193092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05838528460772626,"score_gpt":0.395363960650403,"score_spread":0.3369786760426767,"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."}}