{"id":"W2126266514","doi":"10.5539/ijps.v4n3p1","title":"Challenges of the Fennema-Sherman Test in the International Comparisons","year":2012,"lang":"en","type":"article","venue":"International Journal of Psychological Studies","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Confirmatory factor analysis; Quartile; Mathematics education; Achievement test; Social psychology; Standardized test; Statistics; Mathematics","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":[0.07373846,0.0008821805,0.001583867,0.004318799,0.00145942,0.004287463,0.003836079,0.001132578,0.009176765],"category_scores_gemma":[0.216056,0.0004069052,0.001050722,0.004358639,0.00373077,0.005336155,0.004387889,0.004333693,0.001898055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041919,"about_ca_system_score_gemma":0.004165554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00330671,"about_ca_topic_score_gemma":0.002110825,"domain_scores_codex":[0.8986508,0.07083736,0.008517517,0.005355051,0.01497074,0.001668482],"domain_scores_gemma":[0.8049521,0.1360668,0.01310891,0.01848701,0.02424727,0.003137867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001421205,0.0005657517,0.2052336,0.001158137,0.0007132676,0.001329183,0.005632073,0.002456524,0.0007448625,0.1402664,0.04189384,0.5985851],"study_design_scores_gemma":[0.0004153254,0.003181856,0.3557683,0.00467727,0.000447752,0.005408053,0.01738229,0.0292629,0.004535813,0.3544402,0.224012,0.0004681454],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3608303,0.02130382,0.3765431,0.02978466,0.01221286,0.003854817,0.005907966,0.001465548,0.1880968],"genre_scores_gemma":[0.8813562,0.001876722,0.1027548,0.001796284,0.001516125,0.003208642,0.001568812,0.0003774635,0.005545062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07373846,"threshold_uncertainty_score":0.3899709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4064135690179853,"score_gpt":0.561792907533386,"score_spread":0.1553793385154007,"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."}}