{"id":"W2975639539","doi":"10.5430/ijhe.v8n6p85","title":"Measure Reasoning Skill of Mathematics Students","year":2019,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Mathematics Education and Pedagogy","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Test (biology); Mathematics education; Measure (data warehouse); Field (mathematics); Computer science; Psychology; Mathematics; Engineering; Data mining","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":[0.0007917997,0.0005005925,0.000419872,0.001708356,0.0003539649,0.00100783,0.0003789718,0.0004387276,0.004232721],"category_scores_gemma":[0.006037141,0.0001327234,0.0004901488,0.0008094955,0.0002236649,0.0006835844,0.0007374437,0.0007538487,0.001331434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000308341,"about_ca_system_score_gemma":0.0006193441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004514969,"about_ca_topic_score_gemma":0.0006830735,"domain_scores_codex":[0.9990656,0.0001411656,0.0001419276,0.0001128556,0.0004257025,0.0001128349],"domain_scores_gemma":[0.9968137,0.0006809931,0.001114347,0.0001813506,0.0008753662,0.0003341132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001803148,0.002461909,0.8551084,0.0003204472,0.0001172927,0.0002733555,0.002484786,0.0005390513,0.009694041,0.0007064634,0.002083323,0.1260307],"study_design_scores_gemma":[0.00003465162,0.001636634,0.9819716,0.0001070964,0.00005749307,0.0008369617,0.001814061,0.001271546,0.006426398,0.001459677,0.004350552,0.00003337003],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919897,0.0002320326,0.001373872,0.0001058851,0.00001908163,0.0001270921,0.0002428797,0.00003991091,0.005869597],"genre_scores_gemma":[0.9887481,0.0003841836,0.005606938,0.0001132295,0.00001578922,0.0001975518,0.0008028125,0.00001143125,0.004119985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004232721,"threshold_uncertainty_score":0.01415992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0416032286150162,"score_gpt":0.4254031807781495,"score_spread":0.3837999521631333,"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."}}