{"id":"W4416799325","doi":"10.1109/snpd65828.2025.11254871","title":"Cogniroot Edge: A Quest for A Fair AI Grader","year":2025,"lang":"","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Grading (engineering); Usability; Process (computing); Software; Multiple choice","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008103076,0.0004062927,0.0004886806,0.0002848982,0.0006536949,0.0009742361,0.001038189,0.0002179631,0.00008576125],"category_scores_gemma":[0.0002280522,0.0003752039,0.000355243,0.000693655,0.00009179904,0.0004930777,0.0004172338,0.0004302877,0.000246375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462117,"about_ca_system_score_gemma":0.000517366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002367289,"about_ca_topic_score_gemma":0.0000339797,"domain_scores_codex":[0.9969323,0.0001511198,0.0007065419,0.001061198,0.000314116,0.0008347457],"domain_scores_gemma":[0.9980328,0.0003521009,0.0001704218,0.0006816738,0.0006160281,0.0001469925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001930076,0.0001281138,0.0007948068,0.0002701385,0.0001196304,0.00000756381,0.0008800746,0.00015286,0.0002202898,0.9390861,0.01610846,0.04221268],"study_design_scores_gemma":[0.0006575144,0.0002974588,0.000681171,0.0008643633,0.00004774914,0.000008083657,0.0002955051,0.09557738,0.003888012,0.005358584,0.8918298,0.0004943583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003914083,0.001049667,0.9558314,0.007774424,0.006461576,0.001032618,0.000004980486,0.0002345923,0.02721935],"genre_scores_gemma":[0.5437267,0.0000159692,0.006918439,0.002526944,0.0005349637,0.0001146506,0.000001991754,0.00002049122,0.4461398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489129,"threshold_uncertainty_score":0.99987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0224339298937731,"score_gpt":0.3102295826054359,"score_spread":0.2877956527116629,"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."}}