{"id":"W2143619291","doi":"10.1177/0146621603254799","title":"A New Look at the Influence of Guessing on the Reliability of Multiple-Choice Tests","year":2003,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Variance (accounting); Reliability (semiconductor); Test (biology); Statistics; Econometrics; Psychology; Mathematics","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":[],"category_scores_codex":[0.002555059,0.0001898166,0.0003293631,0.00001517966,0.0001218633,0.000007119759,0.0002998236,0.00009254701,0.0001302693],"category_scores_gemma":[0.01520595,0.00008850744,0.00008554533,0.0001652211,0.0002824932,0.00001751964,0.00005159695,0.0002628911,0.000009589175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007474322,"about_ca_system_score_gemma":0.00002247909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008611828,"about_ca_topic_score_gemma":0.0000095326,"domain_scores_codex":[0.9977028,0.0003597997,0.0005625548,0.0003756484,0.0007404686,0.0002587752],"domain_scores_gemma":[0.9914194,0.007170764,0.0002987291,0.0008489329,0.0001745534,0.00008764243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004419374,0.00126311,0.001823675,0.0001246575,0.0000598327,0.000001411911,0.000441791,0.002325042,0.158721,0.80756,0.002265084,0.02497242],"study_design_scores_gemma":[0.0008974235,0.0002596538,0.03010196,0.000112758,0.00005180813,0.000001895843,0.00007026379,0.00002706796,0.02163042,0.9450065,0.00164887,0.0001913411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7027586,0.00005597592,0.2801444,0.0004337771,0.00007159766,0.001061486,0.000008101655,0.00003238103,0.01543365],"genre_scores_gemma":[0.8681635,0.000004950616,0.1313249,0.000370653,0.00001504529,0.0000657424,2.047365e-7,0.00001149028,0.00004344301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1654049,"threshold_uncertainty_score":0.9930894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2678450942987462,"score_gpt":0.4308893442137286,"score_spread":0.1630442499149824,"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."}}