{"id":"W2943253458","doi":"10.1080/08982112.2018.1548022","title":"Statistical reasoning in diagnostic problem-solving—The case of flow-rate measurements","year":2019,"lang":"en","type":"article","venue":"Quality Engineering","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Suspect; Hierarchy; Computer science; Domain (mathematical analysis); Statistical hypothesis testing; Statistical analysis; Flow (mathematics); Econometrics; Management science; Statistics; Mathematics; Engineering; Psychology; Economics","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":[0.002974866,0.0001482071,0.0002306273,0.00008571085,0.00005207796,0.00007155687,0.0003907248,0.00005438978,0.00001510887],"category_scores_gemma":[0.001596818,0.0001264992,0.00003679619,0.0003308253,0.00001576985,0.0002067607,0.0001200655,0.0002688236,0.00002174041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006044626,"about_ca_system_score_gemma":0.00005643274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006270829,"about_ca_topic_score_gemma":0.0000442283,"domain_scores_codex":[0.9984781,0.0002086333,0.0004758847,0.0002889981,0.0002052008,0.0003431903],"domain_scores_gemma":[0.9967445,0.002561514,0.0001087681,0.0004585922,0.0000576011,0.00006905795],"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":[0.00002007965,0.0001062549,0.06216326,0.000943682,0.00007193895,0.0005559604,0.007360254,0.8528822,0.003710976,0.05661419,0.0001989733,0.01537222],"study_design_scores_gemma":[0.0004632018,0.00006961709,0.01847199,0.0005538507,0.000008743306,0.0000865921,0.00009425917,0.978483,0.0007988369,0.0005134532,0.0001429499,0.0003135111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3755772,0.0001918283,0.6232468,0.000117711,0.0002368463,0.0002464389,0.000008678378,0.0001044644,0.0002700927],"genre_scores_gemma":[0.8862379,0.00000225782,0.1136611,0.00003440627,0.00001857558,0.00001269952,0.000003586561,0.00001118893,0.00001831826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5106607,"threshold_uncertainty_score":0.5158487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02690985421279948,"score_gpt":0.2714776724664599,"score_spread":0.2445678182536604,"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."}}