{"id":"W4380684403","doi":"10.5430/wjel.v13n6p402","title":"Rasch Calibration and Differential Item Functioning (DIF) Analysis of the Indonesian National Assessment Program-Language (INAP-L)","year":2023,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rasch model; Differential item functioning; Item response theory; Psychometrics; Polytomous Rasch model; Psychology; Calibration; Internal consistency; Item bank; Statistics; Clinical psychology; Developmental psychology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006106683,0.0001111449,0.0002686631,0.0006169031,0.0001129271,0.00006850556,0.0001304188,0.00004323299,0.0007104694],"category_scores_gemma":[0.0007895224,0.0000812939,0.0002155448,0.001568863,0.00007016407,0.0001332057,0.00006920887,0.0002935168,5.978092e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004747479,"about_ca_system_score_gemma":0.0000498227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007358273,"about_ca_topic_score_gemma":0.0002743723,"domain_scores_codex":[0.9985896,0.0002190461,0.0004516779,0.0001489654,0.0004120037,0.0001786858],"domain_scores_gemma":[0.9983982,0.0005850563,0.0004168754,0.0001329036,0.0004102176,0.00005669515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001623036,0.000573126,0.8096464,0.00010752,0.003327283,0.000105517,0.07565641,0.0003599184,0.002970654,0.004401217,0.001673185,0.1010165],"study_design_scores_gemma":[0.0009519176,0.0001013897,0.9613808,0.00007712834,0.0005858739,0.000008246372,0.03390723,0.002287218,0.0001292236,0.0000494538,0.0004059274,0.0001156351],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915854,0.0002209261,0.0002136884,0.0001057362,0.0007583003,0.0001541284,0.00002638715,0.00003970886,0.006895767],"genre_scores_gemma":[0.9983314,0.000003110894,0.000178791,0.00004644198,0.0005844316,0.00001260071,0.00003241067,0.00001343849,0.0007973547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1517344,"threshold_uncertainty_score":0.7779142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789979185604344,"score_gpt":0.3233153505967412,"score_spread":0.3054155587406978,"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."}}