{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003761451,0.0002220965,0.000271196,0.0001120985,0.0001728233,0.0002310063,0.001340265,0.00006088823,0.00001801842],"category_scores_gemma":[0.0003533239,0.00016128,0.00007282497,0.0006107846,0.00009143498,0.0004299194,0.0002929621,0.0005825488,0.00004452946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007416338,"about_ca_system_score_gemma":0.0001517007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006851744,"about_ca_topic_score_gemma":0.000008573265,"domain_scores_codex":[0.998006,0.00003496406,0.0005022431,0.0005704494,0.0005647519,0.0003215196],"domain_scores_gemma":[0.998804,0.00008067536,0.0003089128,0.0001366754,0.0005687996,0.0001009369],"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":[0.0001081979,0.0002439268,0.009411515,0.000063004,0.00003347905,0.000001410685,0.02447137,0.1027686,0.01238518,0.8411382,0.000009201567,0.009365871],"study_design_scores_gemma":[0.00005303092,0.0004140629,0.0008712307,0.0005322918,0.000007221599,0.000002916717,0.004714152,0.9630285,0.02657889,0.003464401,0.0000913324,0.0002420013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4271465,0.00006550354,0.5609885,0.006768378,0.000319953,0.0007060154,0.000001843067,0.000132196,0.003871187],"genre_scores_gemma":[0.9955352,0.00001359262,0.003754855,0.0001380015,0.0001042512,0.00003874791,3.159126e-7,0.00001399886,0.000401061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8602598,"threshold_uncertainty_score":0.6576809,"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."}}