{"id":"W1836689784","doi":"10.5539/ass.v11n24p18","title":"A Marking Scheme Rubric: To Assess Students' Mathematical Knowledge for Applied Algebra Test","year":2015,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Grading (engineering); Mathematics education; Comprehension; Test (biology); Vagueness; Computer science; Consistency (knowledge bases); Mathematics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003607098,0.0001197265,0.0001782494,0.0001167767,0.001408829,0.0004675988,0.001082714,0.00007992874,0.00009869303],"category_scores_gemma":[0.0009947128,0.0001197914,0.00005500029,0.001251775,0.0008911935,0.0003126601,0.0001810558,0.00009953362,0.0002468281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004498207,"about_ca_system_score_gemma":0.002074511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007317084,"about_ca_topic_score_gemma":0.0002802387,"domain_scores_codex":[0.9976013,0.00005908001,0.0002128179,0.0003775355,0.001131103,0.0006182126],"domain_scores_gemma":[0.9985461,0.0003924703,0.00008303911,0.0001229817,0.0003824646,0.0004729912],"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":[0.00000693726,0.000301786,0.00776267,0.000009127271,0.000005754891,3.799181e-7,0.05618516,3.089011e-8,0.0004006801,0.9076611,0.005500089,0.02216623],"study_design_scores_gemma":[0.001017587,0.0001822215,0.08570555,0.0000484905,0.00004452845,0.000001528164,0.2742576,0.00002590332,0.0002611266,0.2105931,0.4269259,0.0009364374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03222793,0.00001182335,0.003298238,0.007031882,0.0005615207,0.0007961441,0.000006699967,0.00009095017,0.9559748],"genre_scores_gemma":[0.9860864,8.475648e-7,0.008721238,0.0003489663,0.001295455,0.0001846922,0.000002978075,0.00001167875,0.003347712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9538585,"threshold_uncertainty_score":0.9998912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1475463523479698,"score_gpt":0.4806573111346779,"score_spread":0.333110958786708,"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."}}