{"id":"W2965396085","doi":"","title":"Balancing Student Success and Inferring Personalized Effects in Dynamic Experiments.","year":2019,"lang":"en","type":"article","venue":"Educational Data Mining","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","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":[0.0006751697,0.0001115911,0.0001855804,0.0001203241,0.00004997831,0.00006206808,0.0002873266,0.00003452239,0.0002751424],"category_scores_gemma":[0.00272201,0.0001121469,0.00001060467,0.0001039391,0.00003446209,0.0002042918,0.0002273742,0.0000919148,0.00002244733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008834209,"about_ca_system_score_gemma":0.0001669547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002801819,"about_ca_topic_score_gemma":0.00001727076,"domain_scores_codex":[0.9989711,0.000126526,0.0002226086,0.0003232259,0.0001879747,0.0001685416],"domain_scores_gemma":[0.9953006,0.004141278,0.00009459381,0.0003806045,0.00003278567,0.00005015086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000252929,0.0004231831,0.8559341,0.0006602836,0.00008071084,0.000003153354,0.02665804,0.000008765712,0.002089069,0.1033463,0.005031652,0.005739443],"study_design_scores_gemma":[0.00135028,0.00003668946,0.9588903,0.0004944252,0.00003809828,0.00001495175,0.01628557,0.002889239,0.000169338,0.01798123,0.001447649,0.0004022682],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947808,0.0004001597,0.002131349,0.0003089743,0.001266624,0.0002609219,0.00004086315,0.00002093298,0.0007893968],"genre_scores_gemma":[0.787412,0.00002374126,0.2107517,0.0001172889,0.00006360373,0.00005051009,0.0002764897,0.00001693684,0.001287722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2086203,"threshold_uncertainty_score":0.4573216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1691349651200919,"score_gpt":0.4997090568121423,"score_spread":0.3305740916920505,"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."}}