{"id":"W4361991005","doi":"10.2196/44084","title":"Scoring Single-Response Multiple-Choice Items: Scoping Review and Comparison of Different Scoring Methods","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multiple choice; PsycINFO; Metric (unit); Test (biology); MEDLINE; Medicine; Psychology; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01522839,0.0001681449,0.0007455336,0.0006977845,0.000146804,0.00008427229,0.0005555344,0.000118866,0.0002289286],"category_scores_gemma":[0.5958943,0.000122217,0.00009126034,0.0029883,0.0001426923,0.000180517,0.0002856705,0.0002850724,0.00001705515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000532705,"about_ca_system_score_gemma":0.000349328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003329792,"about_ca_topic_score_gemma":0.00001033185,"domain_scores_codex":[0.9942268,0.002168698,0.001324706,0.0005568676,0.001407133,0.000315805],"domain_scores_gemma":[0.8558693,0.1418782,0.0008121192,0.0006862627,0.0003280248,0.0004261345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002917766,0.0001766056,0.1842051,0.001023336,0.000009315521,5.586344e-7,0.000627388,0.000002993874,0.001816049,0.00002999486,0.00154548,0.810534],"study_design_scores_gemma":[0.0007793489,0.0003521631,0.9330398,0.04636957,0.00007776279,0.00002126281,0.00362554,0.007713399,0.002397902,0.00208766,0.003064344,0.0004711936],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9679292,0.01693414,0.008997628,0.002997422,0.00194042,0.0008031813,0.000001208036,0.0001217185,0.0002750878],"genre_scores_gemma":[0.9713147,0.001196134,0.02595492,0.000677122,0.0003121723,0.0002207787,0.000005992597,0.00002331179,0.0002948639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8100628,"threshold_uncertainty_score":0.5277885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5643011162701261,"score_gpt":0.625437994430518,"score_spread":0.06113687816039182,"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."}}