{"id":"W2557592775","doi":"10.1007/978-981-10-2594-5_9","title":"Confidence Weighting Procedures for Multiple-Choice Tests","year":2016,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Weighting; Correctness; Multiple choice; Certainty; Computer science; Confidence interval; Statistics; Calculus (dental); Mathematics education; Mathematics; Algorithm; Medicine; Significant difference","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":[0.02709113,0.001862672,0.001947024,0.003459778,0.0007615489,0.003056535,0.004359368,0.002598518,0.02074145],"category_scores_gemma":[0.1692094,0.001173691,0.002059282,0.005082869,0.001935134,0.005292634,0.002365645,0.006362651,0.004331307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001391018,"about_ca_system_score_gemma":0.001694675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002216171,"about_ca_topic_score_gemma":0.002111786,"domain_scores_codex":[0.9759034,0.0168395,0.0009712075,0.001358771,0.004557659,0.000369514],"domain_scores_gemma":[0.8901814,0.09520534,0.001842996,0.006245996,0.006128094,0.0003962376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001320599,0.0001352545,0.0008199043,0.0004904333,0.0002158902,0.00007361732,0.0003330481,0.01739648,0.0009460186,0.3992944,0.0158484,0.5643145],"study_design_scores_gemma":[0.00005521754,0.00007741561,0.00105655,0.0002563211,0.00008032833,0.0001676456,0.00007352125,0.1450515,0.00155917,0.8358197,0.01572587,0.00007669457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005478174,0.0005469772,0.9966608,0.0001300756,0.00008649721,0.00004286788,0.00007792885,0.0002149868,0.001692037],"genre_scores_gemma":[0.03523857,0.001187112,0.9559318,0.000231836,0.0003258076,0.0007199103,0.0004503142,0.0005957158,0.005318826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02709113,"threshold_uncertainty_score":0.1432733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3333715532601957,"score_gpt":0.4537833347789388,"score_spread":0.1204117815187432,"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."}}