{"id":"W2924851748","doi":"","title":"An Investigation of Item Bias in PISA Science Test in Terms of The Language and Culture","year":2017,"lang":"en","type":"article","venue":"Kastamonu Education Journal","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Differential item functioning; Psychology; Test (biology); Turkish; Consistency (knowledge bases); Item analysis; Logistic regression; Social psychology; Statistics; Linguistics; Psychometrics; Developmental psychology; Item response theory; Mathematics; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007160284,0.00004793745,0.00006857108,0.0001993544,0.0001874158,0.0001080065,0.0009314552,0.00003260263,0.000002909155],"category_scores_gemma":[0.0005069526,0.00003382994,0.00001181537,0.0002953138,0.0003592752,0.0008736649,0.00008122969,0.0001797815,2.394026e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004903725,"about_ca_system_score_gemma":0.0007682648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004426848,"about_ca_topic_score_gemma":0.0000628253,"domain_scores_codex":[0.9993685,0.00004357334,0.0002045259,0.0001199825,0.0001754619,0.00008791661],"domain_scores_gemma":[0.9990796,0.00004401655,0.000360495,0.0003737482,0.0000875556,0.00005459548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[5.018762e-7,0.0001057457,0.9546431,0.000006204782,6.320299e-7,2.635937e-7,0.007724136,0.000005202983,0.01957245,0.009858861,0.00007338585,0.008009531],"study_design_scores_gemma":[0.00009788122,0.00003004696,0.9648968,0.0001145901,9.819501e-7,0.00002606038,0.001556237,0.0003244691,0.01575275,0.01714498,0.00001920176,0.00003603042],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938556,0.00004152436,0.0001274526,0.005329945,0.0002747637,0.00006489114,6.642001e-7,0.000003297881,0.0003018545],"genre_scores_gemma":[0.9938659,0.00001213536,0.005942107,0.00008179605,0.00003141284,0.000003731412,3.029216e-7,0.000001503526,0.0000610994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01025368,"threshold_uncertainty_score":0.1730891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02253515573390952,"score_gpt":0.3387205955694884,"score_spread":0.3161854398355788,"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."}}