{"id":"W2997778743","doi":"10.1609/aaai.v34i01.5406","title":"Predictive Student Modeling in Educational Games with Multi-Task Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Formative assessment; Computer science; Task (project management); TRACE (psycholinguistics); Test (biology); Artificial intelligence; Machine learning; Mathematics education; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001797547,0.001100305,0.0008490292,0.0006888628,0.000379264,0.001326677,0.00157366,0.001123013,0.0009853796],"category_scores_gemma":[0.005947911,0.0006603657,0.0008459347,0.0005675813,0.0006875863,0.002054164,0.001366995,0.002259722,0.0003353019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001213386,"about_ca_system_score_gemma":0.0009990642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120269,"about_ca_topic_score_gemma":0.01548011,"domain_scores_codex":[0.9993154,0.0002807121,0.00003546272,0.0002047534,0.00007526713,0.00008838544],"domain_scores_gemma":[0.9976927,0.001640637,0.0001916029,0.0001421539,0.0002104146,0.000122476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002019235,0.0002010573,0.003097904,0.00005168297,0.00006971252,0.00007208448,0.0002519212,0.929126,0.001327234,0.002187179,0.0004559273,0.06295727],"study_design_scores_gemma":[0.000003470247,0.0000216657,0.0002181385,0.000002369145,0.000003847963,0.000004121547,0.00000935705,0.9974594,0.0002151978,0.001996607,0.00006184676,0.000004036159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3149843,0.0005222117,0.6801284,0.0006991284,0.00008390794,0.0001420238,0.0002537883,0.001467662,0.001718633],"genre_scores_gemma":[0.9523509,0.0001224169,0.04542823,0.0001385628,0.00003152236,0.0001288924,0.0001910227,0.00004591475,0.001562478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01120269,"threshold_uncertainty_score":0.02227497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1095673077747894,"score_gpt":0.3015430369774162,"score_spread":0.1919757292026268,"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."}}