{"id":"W3208880666","doi":"10.5539/jel.v10n6p103","title":"Designing Standards-Setting for Levels of Mathematical Proficiency in Measurement and Geometry: Multidimensional Item Response Model","year":2021,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council of Thailand; Khon Kaen University","keywords":"Mathematical model; Set (abstract data type); Reliability (semiconductor); Quality (philosophy); Computer science; Process (computing); Construct (python library); Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0423117,0.0009770241,0.001197377,0.003533345,0.001306983,0.004162898,0.002215513,0.002211035,0.002652653],"category_scores_gemma":[0.1031006,0.0007598143,0.002409265,0.003186564,0.002147258,0.003833521,0.003126251,0.00212933,0.0008598894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003727339,"about_ca_system_score_gemma":0.004970601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002254708,"about_ca_topic_score_gemma":0.001922802,"domain_scores_codex":[0.9492537,0.03764705,0.003086855,0.003153573,0.006033938,0.0008249059],"domain_scores_gemma":[0.9154586,0.05903626,0.005722858,0.006066956,0.01284072,0.0008746261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005909091,0.001872585,0.4899344,0.002092836,0.001128952,0.0004078103,0.02107912,0.06651696,0.005985423,0.117956,0.006969191,0.2854658],"study_design_scores_gemma":[0.0006048997,0.003139271,0.2856404,0.001621676,0.0006443845,0.0005330806,0.01933711,0.5275335,0.009515256,0.1297599,0.02109794,0.0005725867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4123564,0.0003189853,0.5692402,0.001753267,0.0001414481,0.004145836,0.0006493224,0.0004963208,0.01089817],"genre_scores_gemma":[0.7378759,0.0001302625,0.2553439,0.000171059,0.00001901372,0.005022556,0.0007287943,0.00004041244,0.0006682179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0423117,"threshold_uncertainty_score":0.2237683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08451347358686771,"score_gpt":0.4060367442683351,"score_spread":0.3215232706814674,"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."}}