{"id":"W2810091567","doi":"10.48550/arxiv.2102.01270","title":"Predicting student performance using data from an auto-grading system","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Grading (engineering); Machine learning; Confusion matrix; Decision tree; Artificial intelligence; Linear regression","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":[0.0002334234,0.0001203736,0.000155728,0.00007241213,0.0003022497,0.0001779043,0.001512742,0.00005238022,0.000006338563],"category_scores_gemma":[0.0000222645,0.000139361,0.00003677556,0.0006121507,0.00002545522,0.001199496,0.001041341,0.0001996586,0.00002639939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001206259,"about_ca_system_score_gemma":0.0001345335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001257673,"about_ca_topic_score_gemma":0.00002874828,"domain_scores_codex":[0.9986661,0.0001198344,0.0001346523,0.0007305628,0.0001064395,0.0002423782],"domain_scores_gemma":[0.9983039,0.0000608504,0.0001075738,0.001315801,0.00008746167,0.0001243768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005516534,0.0001493897,0.6980005,0.0000510319,0.0001144805,0.001005419,0.00056105,0.2778345,0.0007616444,0.0205456,0.00002148423,0.0009493462],"study_design_scores_gemma":[0.0002231029,0.00002309393,0.01284386,0.0001036743,0.00004977752,0.00001382626,0.0008255572,0.9854877,0.00008612075,0.00008596254,0.000100026,0.0001572892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7673239,0.00002571307,0.2318721,0.0000393573,0.000217731,0.00002486119,0.000008795764,0.0002128856,0.0002746531],"genre_scores_gemma":[0.993789,0.00001472349,0.005724943,0.00002839012,0.0001413827,2.557814e-8,0.0000297184,0.000009137125,0.0002626768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7076532,"threshold_uncertainty_score":0.5682975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1237399419327341,"score_gpt":0.2382983231768739,"score_spread":0.1145583812441398,"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."}}