{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001792925,0.001756068,0.0008463427,0.003651742,0.001242085,0.00148077,0.002150021,0.00318283,0.01029444],"category_scores_gemma":[0.01124177,0.0004007291,0.001267306,0.003239847,0.0006494691,0.001830461,0.002355546,0.0025369,0.01147861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001957391,"about_ca_system_score_gemma":0.001939821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01143635,"about_ca_topic_score_gemma":0.03075565,"domain_scores_codex":[0.9973787,0.0006955819,0.0003107324,0.0006124271,0.0008120521,0.0001905242],"domain_scores_gemma":[0.9923146,0.003382601,0.0005341768,0.00123827,0.001617551,0.0009128039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006531769,0.001928032,0.0232588,0.002097477,0.0001830334,0.000471698,0.00103534,0.005690988,0.004338498,0.003360569,0.8664424,0.09053991],"study_design_scores_gemma":[0.001124309,0.0006966321,0.06825284,0.000444045,0.0001139125,0.0007963714,0.001632469,0.03204569,0.008844897,0.008300261,0.8775686,0.0001799325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05402428,0.001189851,0.008984335,0.001849543,0.0003147759,0.001044363,0.9172924,0.005532716,0.009767785],"genre_scores_gemma":[0.0239249,0.0001437804,0.01160978,0.0003329678,0.00005679938,0.0009485288,0.9601755,0.0001254206,0.002682294],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01143635,"threshold_uncertainty_score":0.03443831,"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."}}