{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082102,0.0001840003,0.0004691937,0.0001607386,0.00007558054,0.00017938,0.00007385847,0.0001142973,0.000007641274],"category_scores_gemma":[0.0002934113,0.0001611449,0.0000740527,0.0003558944,0.00001669353,0.0001508166,0.00002477277,0.0002671293,0.000002035256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005534366,"about_ca_system_score_gemma":0.0002793678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003622911,"about_ca_topic_score_gemma":0.00000239413,"domain_scores_codex":[0.9985988,0.00004388635,0.0004582164,0.0002483813,0.0003198935,0.0003308237],"domain_scores_gemma":[0.9992043,0.0002038351,0.00007494038,0.0003129744,0.0001170422,0.00008690589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001667122,0.0005241933,0.07423739,0.02692225,0.002659635,0.0006812949,0.003625638,0.2290469,0.5628244,0.04319387,0.0006056664,0.05401163],"study_design_scores_gemma":[0.003124694,0.0001057125,0.008169998,0.006797498,0.0001936008,0.0001115139,0.001836289,0.9456196,0.003968044,0.00003010618,0.02942631,0.0006166133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8238637,0.0004789851,0.1730847,0.00008609685,0.001182028,0.0002263079,0.000006915539,0.0002851499,0.0007861009],"genre_scores_gemma":[0.9939667,0.00001727244,0.004946298,0.00005970211,0.0003273138,0.00001371903,0.000005023255,0.00003234855,0.0006316496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7165727,"threshold_uncertainty_score":0.65713,"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."}}