{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03741658,0.0006228805,0.0007063803,0.008264165,0.001108666,0.004221463,0.001721224,0.0008319955,0.002523207],"category_scores_gemma":[0.1999288,0.0007479638,0.001639799,0.006322259,0.002038197,0.003215144,0.004111198,0.001890721,0.0004784578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003058731,"about_ca_system_score_gemma":0.002692601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01043816,"about_ca_topic_score_gemma":0.008527434,"domain_scores_codex":[0.9606615,0.0162402,0.003578163,0.002408934,0.01581968,0.00129148],"domain_scores_gemma":[0.7006871,0.207087,0.04435535,0.01366994,0.03144934,0.002751214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004269888,0.00005585984,0.9746601,0.00004931523,0.00009363974,0.00006636975,0.003808717,0.0004716518,0.0002852333,0.001448703,0.0003193657,0.01869841],"study_design_scores_gemma":[0.000004311712,0.0001031713,0.9897703,0.00004990664,0.00002514116,0.0001422853,0.00303944,0.004555251,0.0004035973,0.0008476386,0.001023723,0.00003529524],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9808403,0.0003375392,0.01232815,0.0005073913,0.00002297909,0.0003131847,0.0004700876,0.0000797025,0.005100605],"genre_scores_gemma":[0.9959928,0.00005905103,0.002909049,0.00002047926,0.0000101128,0.0001109973,0.0004269933,0.00003576854,0.0004347384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03741658,"threshold_uncertainty_score":0.1978801,"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."}}