{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005777921,0.0003113756,0.0003627547,0.0007000234,0.0003313925,0.0002208033,0.001427905,0.0002838752,0.0001237088],"category_scores_gemma":[0.00005948116,0.0002813027,0.0001407563,0.0001170658,0.0007399811,0.0001355063,0.0003287661,0.0006361761,0.0002829312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007667366,"about_ca_system_score_gemma":0.0004212971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003086366,"about_ca_topic_score_gemma":0.0002508446,"domain_scores_codex":[0.9977253,0.00001373046,0.0005811343,0.0007205357,0.0006859816,0.0002732847],"domain_scores_gemma":[0.9974198,0.0003577799,0.0005586766,0.00132325,0.0002327705,0.0001077237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[6.073309e-7,0.000125371,0.00002001022,0.00009690112,0.00003338581,0.000007079041,0.0005566371,0.000009509141,0.005112461,0.874425,0.005762017,0.113851],"study_design_scores_gemma":[0.0008149979,0.0001226855,0.002177575,0.001564782,0.0001403184,0.00006161907,0.00003026561,0.2406265,0.02368773,0.3148887,0.4141479,0.001736886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.004957904,0.0001564559,0.07061666,0.001611439,0.01155448,0.001629461,0.0002759532,0.001246412,0.9079512],"genre_scores_gemma":[0.05082561,2.421199e-7,0.130436,0.00003254588,0.00006245895,0.00003368954,0.00006321773,0.00002090672,0.8185253],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5595363,"threshold_uncertainty_score":0.9999639,"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."}}