{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05951421,0.001398052,0.001239081,0.006989547,0.0008061093,0.007054998,0.003336206,0.003515362,0.00488366],"category_scores_gemma":[0.1945858,0.0004612153,0.0006371727,0.004369089,0.003251604,0.007326131,0.002921549,0.002574365,0.002630769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002284631,"about_ca_system_score_gemma":0.003589103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002636017,"about_ca_topic_score_gemma":0.002160897,"domain_scores_codex":[0.9566417,0.03041275,0.002153307,0.001925783,0.008348688,0.0005177679],"domain_scores_gemma":[0.7734265,0.1412965,0.01515012,0.01038767,0.05477065,0.004968605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002079735,0.0001981857,0.01445109,0.0005183487,0.0000601301,0.00003717383,0.0004447543,0.004242156,0.0009994615,0.008236101,0.01182421,0.9587803],"study_design_scores_gemma":[0.0006179785,0.002913273,0.1575929,0.006719451,0.0002851839,0.001467827,0.003072107,0.307238,0.008224366,0.2928403,0.2181267,0.0009019316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1134043,0.1210997,0.6425041,0.06648628,0.004146755,0.001356276,0.00147103,0.008384572,0.04114687],"genre_scores_gemma":[0.4219981,0.02143787,0.5429711,0.003127821,0.003064231,0.00116636,0.001140358,0.0003732296,0.004720897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05951421,"threshold_uncertainty_score":0.314745,"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."}}