{"id":"W4399782080","doi":"10.3390/ai5020045","title":"AI Detection of Human Understanding in a Gen-AI Tutor","year":2024,"lang":"en","type":"article","venue":"AI","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"TUTOR; Computer science; Psychology; Artificial intelligence; Mathematics education","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":[0.0002619903,0.00006566544,0.00009268716,0.0001745256,0.00006253786,0.0001343088,0.0001624278,0.00003838839,0.000007837104],"category_scores_gemma":[0.00001030941,0.00006175156,0.00004428657,0.000298705,0.00001278011,0.0003007176,0.00005374308,0.0001928075,0.0000298669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001674924,"about_ca_system_score_gemma":0.000029402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002345051,"about_ca_topic_score_gemma":0.00005141416,"domain_scores_codex":[0.9993132,0.00004036165,0.0001684289,0.0001979547,0.0001376086,0.0001424531],"domain_scores_gemma":[0.9997582,0.00003163475,0.00002665374,0.0001390569,0.00002328964,0.00002115849],"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":[0.000001366507,0.00001258973,0.0005927861,0.00007519424,0.00001443493,0.00003180357,0.002495622,0.0003414444,0.05257291,0.9399568,0.0001368684,0.003768172],"study_design_scores_gemma":[0.0007862263,0.001212462,0.00676917,0.003550076,0.00002953632,0.0000999418,0.001857131,0.4248348,0.2305845,0.0895365,0.2394819,0.001257755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03720761,0.0002215681,0.9600987,0.000506792,0.0008503186,0.00007611567,3.037694e-7,0.0001205032,0.0009180375],"genre_scores_gemma":[0.9978853,0.000001684241,0.0001307331,0.0001332967,0.0001052177,0.000003800945,2.071456e-7,0.000006796707,0.001732907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606777,"threshold_uncertainty_score":0.2518156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04571073162187732,"score_gpt":0.300980527689497,"score_spread":0.2552697960676196,"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."}}