{"id":"W3164791059","doi":"10.1109/mim.2021.9436102","title":"Machine Learning in Measurement Part 2: Uncertainty Quantification","year":2021,"lang":"en","type":"article","venue":"IEEE Instrumentation & Measurement Magazine","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Usability; Computer science; Measurement uncertainty; Uncertainty quantification; Software deployment; Artificial intelligence; Risk analysis (engineering); Machine learning; Human–computer interaction; Software engineering; Mathematics; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.003359282,0.0003301323,0.0003400971,0.00028561,0.0002728089,0.00028142,0.000576228,0.0000978457,0.0001435248],"category_scores_gemma":[0.0008005717,0.0003618884,0.000106236,0.001162891,0.00004655245,0.0008965681,0.0001379388,0.000550377,0.0002127727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156473,"about_ca_system_score_gemma":0.0004604393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001071371,"about_ca_topic_score_gemma":0.0008202814,"domain_scores_codex":[0.9945534,0.0007700647,0.000862712,0.0008750343,0.002428959,0.0005098003],"domain_scores_gemma":[0.9977974,0.00005691015,0.0003924494,0.0006584052,0.0009585918,0.0001362284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001232062,0.0008194029,0.05284063,0.0001706817,0.0001498018,0.000141181,0.001778558,0.5084584,0.1824262,0.01487327,0.001391264,0.2368274],"study_design_scores_gemma":[0.008273226,0.0003061981,0.06247851,0.0007041525,0.00009728722,0.00007541882,0.0004452727,0.7735711,0.06668886,0.0024661,0.08320994,0.001683947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03006267,0.0006541347,0.9533539,0.006986437,0.003390301,0.0007276877,0.000004870494,0.0005900821,0.004229889],"genre_scores_gemma":[0.9866019,0.00009259917,0.01237469,0.0003535302,0.000146154,0.00008281785,0.00005086765,0.00003025923,0.0002672157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9565392,"threshold_uncertainty_score":0.9998833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06298068963506236,"score_gpt":0.2769282678517717,"score_spread":0.2139475782167093,"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."}}