{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003194539,0.0005746714,0.001070373,0.0007382794,0.0002669591,0.0003068846,0.001383366,0.0004629055,0.0008209479],"category_scores_gemma":[0.4174628,0.0004255972,0.0001456598,0.000226397,0.0005730305,0.0004973987,0.0003585535,0.0004620787,0.0000963389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427539,"about_ca_system_score_gemma":0.0004070072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001706793,"about_ca_topic_score_gemma":0.0005023202,"domain_scores_codex":[0.9948351,0.0001186495,0.001845702,0.001184486,0.001351414,0.0006646677],"domain_scores_gemma":[0.8200958,0.176454,0.00137353,0.0008956869,0.001025821,0.0001550639],"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":[0.0001112203,0.00001407693,0.003948832,0.0001714265,0.00003561507,0.0000541602,0.0001832746,0.00001057248,0.00004356673,0.8773081,0.04843792,0.06968128],"study_design_scores_gemma":[0.0003359714,0.0001272767,0.000872521,0.0003839273,0.00001697488,0.0000191918,0.00004445627,0.0001246882,0.00002170582,0.5102088,0.4874589,0.0003856252],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000336192,0.003403397,0.4243548,0.0005545928,0.003147728,0.001672266,0.004558935,0.0001930995,0.5620816],"genre_scores_gemma":[0.0007925564,0.001023438,0.2731635,0.000435063,0.0006456515,0.00008683257,0.00003175441,0.0001121067,0.7237091],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.439021,"threshold_uncertainty_score":0.9998196,"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."}}