{"id":"W7097965712","doi":"","title":"TITLE Differential Domain Functioning on the Numeracy Component of the Foundation Skills Assessment: Bringing the Context into","year":2016,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Numeracy; Differential item functioning; Matching (statistics); Context (archaeology); Test (biology); Differential (mechanical device); Contrast (vision); Interpretation (philosophy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006535812,0.0002205595,0.0003833548,0.001682099,0.001083683,0.001684876,0.0004813995,0.0003409466,0.0029994],"category_scores_gemma":[0.03441674,0.0001339608,0.0002623824,0.00159841,0.001829478,0.0009884457,0.002164185,0.001008067,0.0002744644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001663947,"about_ca_system_score_gemma":0.003012941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01916155,"about_ca_topic_score_gemma":0.04720286,"domain_scores_codex":[0.9958485,0.00243917,0.0002651132,0.0004269822,0.0008392304,0.0001810299],"domain_scores_gemma":[0.9823437,0.01143122,0.001667298,0.001336822,0.00278626,0.0004347158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001683563,0.00009551828,0.7855667,0.0002673675,0.00006744621,0.0002323327,0.009044843,0.0006838004,0.002347633,0.01651319,0.002311071,0.1827017],"study_design_scores_gemma":[0.00002138044,0.0003063712,0.9444817,0.000428497,0.00007036068,0.0005891868,0.007313368,0.003066641,0.003822689,0.0171235,0.02272291,0.00005337629],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9352178,0.001205436,0.03712807,0.001859077,0.0002162,0.000185892,0.0008044926,0.00007921926,0.02330378],"genre_scores_gemma":[0.9853603,0.0002117924,0.01238439,0.0002073682,0.0000446747,0.0001212515,0.0001772094,0.00001715385,0.001475797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01916155,"threshold_uncertainty_score":0.03810006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1806498618922558,"score_gpt":0.4197757263088184,"score_spread":0.2391258644165626,"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."}}