{"id":"W4382463660","doi":"10.1609/aaai.v37i13.27091","title":"A Dataset for Learning University STEM Courses at Scale and Generating Questions at a Human Level","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scale (ratio); Science and engineering; Mathematics education; Dozen; Foundation (evidence); Earth system science; Computer science; Data science; Engineering; Engineering ethics; Mathematics; Ecology; Geography; Biology; Cartography","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":[0.0004349101,0.0001296127,0.0001626392,0.0001119064,0.0009413726,0.0001406883,0.0007217014,0.00005428711,0.000007241001],"category_scores_gemma":[0.0001556284,0.0001120543,0.00005435562,0.0004401467,0.0001806546,0.0002005414,0.0006997856,0.0001778664,0.0000337354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005657916,"about_ca_system_score_gemma":0.00004370512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000487651,"about_ca_topic_score_gemma":0.00009496124,"domain_scores_codex":[0.9989213,0.00002025582,0.0002168371,0.0003788533,0.0002154962,0.0002472257],"domain_scores_gemma":[0.9991683,0.0001239845,0.0002186523,0.0001551879,0.0002619104,0.00007193896],"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":[0.00007702196,0.0001488821,0.008837289,0.0001936506,0.00005164328,0.000002911968,0.003943688,0.003821238,0.2076326,0.7171639,0.004950384,0.05317677],"study_design_scores_gemma":[0.00006163392,0.0002489485,0.0004801325,0.0002328167,0.00003181216,0.000006386627,0.001599779,0.9140487,0.06938307,0.01096393,0.002666019,0.0002768218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983009,0.00001074925,0.01089492,0.005087898,0.0001173991,0.0002456166,0.0001905446,0.000138432,0.0003054478],"genre_scores_gemma":[0.9923474,0.00002607323,0.003123695,0.0000434881,0.0000451227,0.000003763715,0.00002332655,0.000008449326,0.004378725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9102274,"threshold_uncertainty_score":0.7240372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1461282570980275,"score_gpt":0.3351370423303442,"score_spread":0.1890087852323167,"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."}}