{"id":"W7103654481","doi":"10.5281/zenodo.17499557","title":"A survey on automates grading of hand written examination answer scripts using machine learning and natural language processing","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Scripting language; Grading (engineering); Natural language; Leverage (statistics); Argumentation theory; Process (computing); Word processing; Question answering","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":[0.01977766,0.0008561597,0.001007246,0.004549587,0.0004528923,0.002056955,0.001788738,0.001136329,0.004048402],"category_scores_gemma":[0.06542313,0.0004204361,0.0006728144,0.003890465,0.000493245,0.002037893,0.000989691,0.0005737982,0.004623243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008300649,"about_ca_system_score_gemma":0.002477604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002791242,"about_ca_topic_score_gemma":0.003485938,"domain_scores_codex":[0.9744989,0.01096892,0.003152843,0.00221836,0.008500917,0.0006601625],"domain_scores_gemma":[0.8790488,0.06198027,0.008382271,0.007037069,0.041519,0.002032485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004611241,0.00043429,0.03133521,0.003135128,0.00009531228,0.00004630598,0.0007448489,0.0008750198,0.004833371,0.0004428609,0.01170129,0.9458952],"study_design_scores_gemma":[0.0003093292,0.004910789,0.4952743,0.009335568,0.0004993075,0.002022865,0.005171979,0.02842843,0.05564757,0.00294439,0.395115,0.000340479],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5612022,0.08144976,0.2735895,0.00479386,0.0008461552,0.003929419,0.007404722,0.01421394,0.0525705],"genre_scores_gemma":[0.6708562,0.04857069,0.2306097,0.002717541,0.0005202594,0.002106558,0.01963256,0.001700983,0.02328534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01977766,"threshold_uncertainty_score":0.1045955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03418531591261612,"score_gpt":0.3069988225832262,"score_spread":0.2728135066706101,"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."}}