{"id":"W4389138268","doi":"10.1007/s11943-023-00331-z","title":"Exploring quality dimensions in trustworthy Machine Learning in the context of official statistics: model explainability and uncertainty quantification","year":2023,"lang":"en","type":"article","venue":"AStA Wirtschafts- und Sozialstatistisches Archiv","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Computer science; Quality (philosophy); Context (archaeology); Data science; Trustworthiness; Data collection; Coding (social sciences); Data quality; Quality management; Process management; Artificial intelligence; Machine learning; Data mining; Engineering; Operations management; Statistics; Computer security","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":[0.004575845,0.000300884,0.0005391778,0.0004759877,0.0003678218,0.0001513355,0.0007890617,0.00006362095,0.000005082418],"category_scores_gemma":[0.002092163,0.0002694495,0.00006241443,0.001227813,0.000397872,0.0007638962,0.0004011251,0.0005701854,0.00001703391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007982065,"about_ca_system_score_gemma":0.0002489957,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008809096,"about_ca_topic_score_gemma":0.01720483,"domain_scores_codex":[0.9953058,0.001434891,0.001199072,0.0007914133,0.0006047646,0.0006640853],"domain_scores_gemma":[0.9947779,0.003838521,0.0003546758,0.0007657322,0.0001457696,0.0001174061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001250892,0.0001873789,0.008642633,0.0001211402,0.0000197343,0.00004591963,0.04203304,0.1119277,0.001347951,0.7553568,0.00005456014,0.08013809],"study_design_scores_gemma":[0.0003445813,0.0001332445,0.03462433,0.00007196086,0.00001090241,0.000002896588,0.008327157,0.8932171,0.0007363296,0.06197046,0.0002350585,0.0003259748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5748447,0.00009631069,0.4232189,0.0009016761,0.000099516,0.0005047978,0.0001594526,0.00009469497,0.00008004744],"genre_scores_gemma":[0.9797059,0.0003260834,0.01956696,0.00007730317,0.00002472304,0.0001421362,0.00009707806,0.00002327699,0.00003648742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7812894,"threshold_uncertainty_score":0.9999757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1553770748700975,"score_gpt":0.3480554712608029,"score_spread":0.1926783963907054,"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."}}