{"id":"W4403873331","doi":"10.1007/s10639-024-13110-2","title":"Stacking: An ensemble learning approach to predict student performance in PISA 2022","year":2024,"lang":"en","type":"article","venue":"Education and Information Technologies","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Educational technology; Stacking; Mathematics education; Computer science; Ensemble learning; Academic achievement; Psychology; Artificial intelligence; Machine learning; Chemistry","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":[0.0003028919,0.00007834897,0.0000718564,0.0005728519,0.00009365409,0.0004527811,0.0003101825,0.00006019017,0.000001445159],"category_scores_gemma":[0.00008532362,0.00007012366,0.00001098863,0.0007414314,0.00002001822,0.002842382,0.0001360093,0.0002641184,0.00003351482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005152222,"about_ca_system_score_gemma":0.0001180692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004674188,"about_ca_topic_score_gemma":7.64985e-7,"domain_scores_codex":[0.9993556,0.00001748073,0.0001974835,0.0001428955,0.0001549778,0.0001315483],"domain_scores_gemma":[0.9996783,0.0000154501,0.00004002466,0.0001887483,0.00004880083,0.00002866388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001021763,0.00007550073,0.007850889,0.00008342959,0.000003759172,1.096733e-7,0.008466453,0.00401023,0.00001951004,0.07978235,0.0005772653,0.8991295],"study_design_scores_gemma":[0.0001196673,0.00027736,0.02526653,0.0001339756,0.000003460909,0.00001560936,0.0254475,0.7579864,0.0003975258,0.001186324,0.1889109,0.000254787],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8592089,0.0004976275,0.1127284,0.008111335,0.0005890728,0.000313001,0.000001037085,0.002751297,0.01579936],"genre_scores_gemma":[0.9879021,0.0002473366,0.01128042,0.0001224525,0.00001926551,0.00003578564,0.00001561746,0.000002975063,0.0003740451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8988747,"threshold_uncertainty_score":0.4366179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009919942040356072,"score_gpt":0.278071289975247,"score_spread":0.2681513479348909,"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."}}