{"id":"W7122019785","doi":"10.1093/teamat/hraf020","title":"Using Möbius for automated assessment in mathematics: a case study","year":2025,"lang":"en","type":"article","venue":"Teaching Mathematics and its Applications An International Journal of the IMA","topic":"Mathematics Education and Programs","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Summative assessment; Formative assessment; Enthusiasm; Grading (engineering); Alphanumeric; Context (archaeology); Grade inflation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002541161,0.0001952563,0.0003756,0.0003372363,0.0002790265,0.0002469336,0.0007211002,0.00006427524,0.00001214863],"category_scores_gemma":[0.0005895493,0.0001397703,0.0001300538,0.0001932573,0.00003754415,0.0002273068,0.0001427469,0.0003613053,5.447292e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001755773,"about_ca_system_score_gemma":0.0001984551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002531,"about_ca_topic_score_gemma":0.00003848282,"domain_scores_codex":[0.9980332,0.0001056698,0.001159979,0.0001787637,0.0003549619,0.0001673702],"domain_scores_gemma":[0.9973702,0.0007640023,0.0008990424,0.0004003482,0.000498187,0.00006826553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001435019,0.01018445,0.0007910065,0.0006098485,0.0004958363,0.00003252173,0.01737905,0.0001536785,0.0007606964,0.9647295,0.0002327882,0.00461627],"study_design_scores_gemma":[0.002294206,0.0001357672,0.0001762163,0.0006743902,0.0003753078,0.002516723,0.0289942,0.5901182,0.0001087319,0.3736296,0.0006829298,0.0002937381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7443665,0.00005521197,0.2520136,0.0005529936,0.0002882075,0.001977788,0.00001602065,0.00006265105,0.0006670241],"genre_scores_gemma":[0.5790029,0.000006847729,0.4205428,0.00004562782,0.00006749488,0.0001351254,0.000001186701,0.00002289096,0.0001750655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5910999,"threshold_uncertainty_score":0.5699669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1037123727496623,"score_gpt":0.4885086332382877,"score_spread":0.3847962604886254,"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."}}