{"id":"W2167507251","doi":"10.1111/medu.12517","title":"Automated essay scoring and the future of educational assessment in medical education","year":2014,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada; University of Alberta","funders":"","keywords":"Summative assessment; Formative assessment; Computer science; Process (computing); Context (archaeology); Scoring system; Writing assessment; Educational measurement; Artificial intelligence; Natural language processing; Machine learning; Mathematics education; Curriculum; Psychology; Medicine; Pedagogy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003247858,0.00008300824,0.0001642869,0.0001018235,0.0001928185,0.00004446965,0.0003106954,0.0001560306,0.001711079],"category_scores_gemma":[0.002603784,0.00006068587,0.00003201485,0.0003606279,0.0004784511,0.0001384338,0.00004613607,0.0002516379,0.000008097481],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578628,"about_ca_system_score_gemma":0.01241013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001613262,"about_ca_topic_score_gemma":0.001806709,"domain_scores_codex":[0.9975402,0.0005262927,0.0003242319,0.0001807286,0.00125531,0.0001731988],"domain_scores_gemma":[0.9988843,0.0005535576,0.000132433,0.0001321625,0.000127712,0.0001698929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001491421,0.0008687578,0.2090398,0.00003781899,0.00001194825,6.532783e-8,0.01104376,5.021541e-7,0.000002635624,0.614473,0.01724652,0.1472602],"study_design_scores_gemma":[0.001659379,0.00003038018,0.8698143,0.0004131703,0.00003246984,0.000003347403,0.02255609,0.005027284,0.000002854037,0.0167968,0.0834605,0.0002034565],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5630151,0.0009811503,0.00008898578,0.3599799,0.005178316,0.0005364445,4.120704e-7,0.00005643197,0.07016329],"genre_scores_gemma":[0.9942191,0.0003835559,0.0004066657,0.002277235,0.001793189,0.0001131998,0.00002266636,0.000006207894,0.0007781372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6607745,"threshold_uncertainty_score":0.9992015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007292918176272418,"score_gpt":0.3889499880168408,"score_spread":0.3816570698405684,"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."}}