{"id":"W4415906860","doi":"10.15390/es.2014.1247","title":"Comparability between the American and Turkish Versions of the TIMSS Mathematics Test Results","year":2014,"lang":"","type":"article","venue":"TED EĞİTİM VE BİLİM","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Ottawa Hospital","funders":"","keywords":"Comparability; Turkish; Test (biology); Student's t-test","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01894754,0.0005679319,0.001620027,0.0004368612,0.00125699,0.0003563942,0.003418948,0.0002220517,0.0001177775],"category_scores_gemma":[0.2291421,0.0003001466,0.0004221421,0.007579492,0.003932327,0.0001904437,0.001581221,0.0009755933,0.00009076094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008246319,"about_ca_system_score_gemma":0.0001753074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003324342,"about_ca_topic_score_gemma":0.0000305749,"domain_scores_codex":[0.9904828,0.002738453,0.002550129,0.00123634,0.002090503,0.0009017527],"domain_scores_gemma":[0.7797641,0.2116169,0.003434855,0.003986229,0.0008001361,0.0003978455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002109011,0.0008088152,0.7309536,0.0001292144,0.0002199638,0.000002774839,0.00575616,0.0002339124,0.0007481998,0.0006284784,0.02337464,0.2369333],"study_design_scores_gemma":[0.001179953,0.0007257325,0.9497491,0.0002291946,0.0002532962,0.00001635034,0.005508199,0.01367042,0.0004822648,0.01561601,0.01210826,0.000461227],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977505,0.0003560799,0.004207292,0.00501617,0.0009537702,0.000878732,0.0005915124,0.0000886663,0.01040282],"genre_scores_gemma":[0.9864079,0.0001058279,0.01246297,0.0003138031,0.000287286,0.000009980929,0.000006629963,0.00003022165,0.0003753918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2364721,"threshold_uncertainty_score":0.999945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3692658733058659,"score_gpt":0.4405121815083178,"score_spread":0.07124630820245192,"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."}}