{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04375805,0.00157264,0.001741575,0.0057918,0.003158379,0.00657837,0.004768177,0.005843971,0.003587386],"category_scores_gemma":[0.1936888,0.001607281,0.003398492,0.004627163,0.020782,0.0139036,0.005454208,0.006686071,0.0004312667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004755419,"about_ca_system_score_gemma":0.005324169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007850216,"about_ca_topic_score_gemma":0.004481493,"domain_scores_codex":[0.9465172,0.0375949,0.003031283,0.004528026,0.006975905,0.001352643],"domain_scores_gemma":[0.7243391,0.249576,0.008602546,0.009339681,0.006498951,0.001643617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00021609,0.0001936216,0.006293893,0.0009678111,0.000320985,0.001399559,0.005263843,0.08536341,0.001278228,0.8109375,0.00295969,0.08480527],"study_design_scores_gemma":[0.00006717436,0.00005148075,0.0006645713,0.0001292058,0.00005277728,0.0002925436,0.0006748215,0.1302475,0.001354152,0.8619605,0.004452132,0.00005324039],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02051545,0.001004551,0.9608088,0.01104051,0.0001093202,0.000177705,0.0001270025,0.0003637965,0.005852958],"genre_scores_gemma":[0.3164807,0.0005274736,0.6806396,0.0009197334,0.0001470317,0.0002683854,0.0001462509,0.0001211346,0.0007498028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04375805,"threshold_uncertainty_score":0.2314175,"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."}}