{"id":"W2147628522","doi":"","title":"Some drivers of test item difficulty in mathematics : an analysis of the competency rubric","year":2012,"lang":"en","type":"article","venue":"ACEReSearch (Australian Council for Educational Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Test (biology); Inclusion (mineral); Mathematics education; Test preparation; Psychology; Pedagogy; Computer science; Medical education; Engineering; Social psychology; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009152442,0.0001135985,0.0002860887,0.0004715073,0.0004816415,0.00007093784,0.001186869,0.0001057377,0.001525858],"category_scores_gemma":[0.00895057,0.0000894094,0.0002006029,0.002996424,0.001154669,0.0005722618,0.0001527094,0.0003362625,0.00002708121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153621,"about_ca_system_score_gemma":0.004147247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162846,"about_ca_topic_score_gemma":0.007404346,"domain_scores_codex":[0.9934162,0.0004569809,0.000413431,0.0002314196,0.004604148,0.0008778214],"domain_scores_gemma":[0.9912003,0.005345425,0.0001487045,0.0004213811,0.002595613,0.0002885777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001770966,0.001951914,0.813169,0.00008327176,0.0001733352,9.879776e-8,0.02695471,0.00001676349,0.001594415,0.1409698,0.01499944,0.00006946819],"study_design_scores_gemma":[0.0002828153,0.00008407081,0.9449779,0.00004157329,0.00007093918,1.038644e-7,0.04231956,0.0001357899,0.0001734502,0.00522829,0.00657298,0.0001125025],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863477,0.0000884189,0.000001072387,0.005986522,0.0001549892,0.0009161863,0.0001743373,0.000006014037,0.006324804],"genre_scores_gemma":[0.9759531,0.0001142522,0.0003671285,0.000009034919,0.0002605894,0.00008703986,0.00004232479,0.00001280376,0.02315375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1357416,"threshold_uncertainty_score":0.9993975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.35000712176952,"score_gpt":0.4785186624063204,"score_spread":0.1285115406368004,"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."}}