{"id":"W2501361141","doi":"10.1142/9789812837066_0005","title":"Automatic Difficulty Level Estimation of Multimedia Math Test Items","year":2010,"lang":"en","type":"book-chapter","venue":"WORLD SCIENTIFIC eBooks","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimation; Test (biology); Computer science; Multimedia; Mathematics education; Mathematics; Statistics; Engineering","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":[0.001823726,0.001008875,0.0006904911,0.003342643,0.0001908117,0.001046937,0.001460616,0.0006641963,0.009069665],"category_scores_gemma":[0.009782,0.0004758062,0.0005929507,0.001354314,0.0001597268,0.0009716654,0.001146677,0.0007234125,0.00493105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004043681,"about_ca_system_score_gemma":0.0002462587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001082222,"about_ca_topic_score_gemma":0.001488606,"domain_scores_codex":[0.9983542,0.0005605166,0.00008337106,0.0003363589,0.0005771644,0.00008832173],"domain_scores_gemma":[0.9930274,0.004214015,0.0003787712,0.0006585589,0.001619947,0.0001012315],"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":[0.0003053656,0.000166405,0.01750628,0.0001813128,0.00005803291,0.00004629002,0.0001240385,0.005053005,0.03301595,0.001217654,0.006486597,0.9358391],"study_design_scores_gemma":[0.0001603812,0.0005946945,0.2484041,0.0001967474,0.0001805858,0.0006111485,0.000254311,0.6325711,0.09317936,0.009626505,0.01405193,0.0001691526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1489146,0.0006628367,0.8323336,0.00017807,0.00009670266,0.0003241256,0.001990242,0.008417156,0.007082877],"genre_scores_gemma":[0.4645815,0.0002991485,0.5161592,0.0001382768,0.0001135603,0.0006306256,0.006343884,0.0008138755,0.01092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009069665,"threshold_uncertainty_score":0.03034103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03323424795749254,"score_gpt":0.2728560834867463,"score_spread":0.2396218355292538,"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."}}