{"id":"W7097092499","doi":"","title":"Moderated DIF 1 Running head: MODERATED DDF METHODOLOGY Differential Domain Functioning on the Numeracy Component of the Foundation Skills Assessment: Bringing the Context into Picture by Investigating Sociological / Community Moderated Test and Item","year":2003,"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":"Differential item functioning; Test (biology); Numeracy; Context (archaeology); Matching (statistics); Item response theory; Contrast (vision); Differential (mechanical device)","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01702227,0.0004211075,0.000760707,0.0001872669,0.004484431,0.0007501087,0.0009939894,0.0002633807,0.0002712632],"category_scores_gemma":[0.08391184,0.0001856322,0.0001630271,0.001628326,0.0008554303,0.0002563476,0.0004470929,0.001845777,0.000003192432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001197182,"about_ca_system_score_gemma":0.0001090129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005965679,"about_ca_topic_score_gemma":0.00004981836,"domain_scores_codex":[0.9805132,0.01607959,0.001308981,0.0006248081,0.000961977,0.0005114469],"domain_scores_gemma":[0.8774567,0.1195775,0.001199466,0.00103481,0.000601603,0.0001298765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002638115,0.001304591,0.454586,0.00006188858,0.0006483605,0.00000258666,0.04568306,0.04454768,0.3301221,0.07299415,0.003396236,0.04638957],"study_design_scores_gemma":[0.001726717,0.0003408367,0.1788422,0.0001720472,0.00006675455,0.00004842842,0.03645298,0.574028,0.007103154,0.2005141,0.0001833675,0.0005213684],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7127314,0.00007742632,0.2833161,0.002084566,0.0003175333,0.0004454514,0.000005737004,0.00006953354,0.0009523364],"genre_scores_gemma":[0.9734608,0.000009040532,0.02467622,0.001610294,0.00003961084,0.00003913531,0.00001792979,0.00002284803,0.0001241091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5294803,"threshold_uncertainty_score":0.9968116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3317731146178872,"score_gpt":0.4374428462040095,"score_spread":0.1056697315861223,"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."}}