{"id":"W4396528990","doi":"10.36834/cmej.77957","title":"Giving partial credit during an multiple choice question assessment reappraisal does not make the assessment process fairer","year":2024,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Process (computing); Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2138726,0.001664795,0.003605434,0.002458654,0.004930374,0.006910197,0.003334992,0.008930599,0.04027841],"category_scores_gemma":[0.6104181,0.001131415,0.002259506,0.002364498,0.006821128,0.009130235,0.007638649,0.01119874,0.01797435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004089206,"about_ca_system_score_gemma":0.007680227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001482588,"about_ca_topic_score_gemma":0.002607047,"domain_scores_codex":[0.6366232,0.2579934,0.02607681,0.008344959,0.06236816,0.008593437],"domain_scores_gemma":[0.3070637,0.4852762,0.03865235,0.05292209,0.1016277,0.01445802],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.009441892,0.002677525,0.0156752,0.003048245,0.000596737,0.0005254643,0.02416892,0.001954196,0.0120057,0.0281998,0.3705326,0.5311736],"study_design_scores_gemma":[0.004636456,0.00501434,0.07942991,0.007035224,0.0006652861,0.001888528,0.02078322,0.02653609,0.02095366,0.2386063,0.5924438,0.002007208],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2456415,0.003042916,0.299215,0.1734556,0.04278952,0.02497884,0.002449419,0.007245997,0.2011813],"genre_scores_gemma":[0.7059265,0.001611991,0.1754741,0.03601846,0.003124849,0.0314044,0.0009541802,0.001448132,0.04403742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7861274,"threshold_uncertainty_score":0.969435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01348481102766568,"score_gpt":0.3957147174347171,"score_spread":0.3822299064070515,"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."}}