{"id":"W4321452091","doi":"10.1080/08957347.2023.2172017","title":"Dissecting Knowledge, Guessing, and Blunder in Multiple Choice Assessments","year":2023,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Toronto","funders":"Division of Molecular and Cellular Biosciences; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Test (biology); Probabilistic logic; Mistake; Psychology; Proxy (statistics); Robustness (evolution); Bayesian probability; Social psychology; Computer science; Artificial intelligence; Machine learning; Political science","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06437974,0.0001732105,0.0008654971,0.0007176268,0.0001015368,0.0003961639,0.0004215868,0.00005801153,0.0002395698],"category_scores_gemma":[0.01557508,0.0001123527,0.0001176422,0.002330443,0.00001892641,0.0001648671,0.00006974534,0.0001303644,0.0006395519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002026802,"about_ca_system_score_gemma":0.0001754238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007092561,"about_ca_topic_score_gemma":0.001603428,"domain_scores_codex":[0.9923301,0.001100123,0.003099388,0.0007346888,0.002497937,0.0002378056],"domain_scores_gemma":[0.9957916,0.001565289,0.001019203,0.0009746587,0.0005698685,0.0000793539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003525796,0.0003805126,0.8331961,0.00009419455,0.00003188405,1.745126e-7,0.002389649,0.0001240489,0.002812528,0.00128522,0.01001464,0.1496675],"study_design_scores_gemma":[0.0003106279,0.000006513758,0.9585586,0.0001120652,0.00003023288,3.893961e-7,0.007457862,0.00381378,0.0001364606,0.005836555,0.02357472,0.0001621543],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586925,0.0006102983,0.0006572054,0.0002429759,0.0008178882,0.000970385,5.814333e-7,0.00001129963,0.03799687],"genre_scores_gemma":[0.9969668,0.00001628959,0.0007082941,0.00006144077,0.00009557604,0.000291867,0.000009463004,0.00001011042,0.001840189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1495054,"threshold_uncertainty_score":0.9927171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8152165292421817,"score_gpt":0.575029629601757,"score_spread":0.2401868996404247,"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."}}