{"id":"W4394817988","doi":"10.1080/10447318.2024.2338330","title":"Transforming Educational Assessment: Insights Into the Use of ChatGPT and Large Language Models in Grading","year":2024,"lang":"en","type":"article","venue":"International Journal of Human-Computer Interaction","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Grading (engineering); Computer science; Artificial intelligence; Mathematics education; Psychology; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003097968,0.00008866046,0.0001550255,0.0005717399,0.00005305548,0.0001196033,0.0001095306,0.00004815365,0.00005750069],"category_scores_gemma":[0.00003143479,0.00006449303,0.00009264208,0.0001235986,0.00003506801,0.001130383,0.00002129037,0.0003837719,0.000002118326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002515917,"about_ca_system_score_gemma":0.000165935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004255282,"about_ca_topic_score_gemma":0.0001957315,"domain_scores_codex":[0.9987479,0.00005400155,0.0006464557,0.000122654,0.000336074,0.00009289531],"domain_scores_gemma":[0.999006,0.0003545997,0.0001801943,0.00007171005,0.0003410704,0.00004646441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003753534,0.0009987627,0.01183603,0.0003889512,0.0006557263,0.0002087591,0.2347422,0.003275441,0.02741009,0.06578628,0.001666421,0.652656],"study_design_scores_gemma":[0.001006972,0.001580877,0.0328487,0.01066771,0.0002867235,0.002786346,0.01989321,0.7985777,0.03815136,0.05958666,0.03404565,0.0005680383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9625326,0.0006932933,0.02912739,0.004809545,0.002582811,0.0001279939,0.000001447134,0.000007368015,0.0001175584],"genre_scores_gemma":[0.9966865,0.0002514905,0.001515466,0.000275169,0.001175203,0.000005305728,0.00001682375,0.00001074678,0.00006328371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7953023,"threshold_uncertainty_score":0.2629949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.138589355159479,"score_gpt":0.4668324641159142,"score_spread":0.3282431089564352,"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."}}