{"id":"W2096160735","doi":"10.1080/15434300701375832","title":"Three Generations of DIF Analyses: Considering Where It Has Been, Where It Is Now, and Where It Is Going","year":2007,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":386,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Contrast (vision); Psychology; Cognitive psychology; Item response theory; Econometrics; Computer science; Psychometrics; Artificial intelligence; Mathematics; Developmental psychology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005792451,0.0004242767,0.0005519639,0.0001943643,0.0002984112,0.000223461,0.0003612596,0.0002868678,0.01493608],"category_scores_gemma":[0.00001015566,0.0003789917,0.0002008102,0.0003921827,0.0001821099,0.0003079022,0.00004759144,0.000456175,0.0002403061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008695065,"about_ca_system_score_gemma":0.0001166745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001096836,"about_ca_topic_score_gemma":0.01301482,"domain_scores_codex":[0.9969435,0.0001482274,0.000929441,0.0008176497,0.0005243055,0.0006369313],"domain_scores_gemma":[0.9979244,0.000459609,0.0004142513,0.0007597716,0.0001867823,0.0002552242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001081645,0.001775553,0.2446399,0.0003096328,0.001423623,0.000288283,0.06773006,0.000005953319,0.02098111,0.004693085,0.6274801,0.03056452],"study_design_scores_gemma":[0.006072184,0.003364352,0.5359789,0.0009524424,0.0008627624,0.0002267555,0.2781354,0.0004938076,0.0007855789,0.007092046,0.1636461,0.002389612],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8150021,0.005624855,0.02692896,0.0475564,0.001170833,0.000859707,0.0002762704,0.0001407408,0.1024401],"genre_scores_gemma":[0.9720086,0.0001037086,0.01214098,0.006666999,0.0004935285,0.000086279,0.00008568882,0.00005445157,0.008359737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.463834,"threshold_uncertainty_score":0.9998662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08492024923436474,"score_gpt":0.4363221750131228,"score_spread":0.351401925778758,"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."}}