{"id":"W2139763558","doi":"10.1007/0-306-47642-8_24","title":"Effects of Adaptations on Comparability of Test Items and Test Scores","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Comparability; Test (biology); Statistics; Psychology; Econometrics; Computer science; Mathematics; Biology; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1830288,0.0016104,0.001971656,0.00234287,0.001272234,0.002524872,0.002749009,0.00226113,0.01026743],"category_scores_gemma":[0.6591649,0.001400841,0.00251423,0.002838413,0.003084396,0.003842362,0.00470127,0.003351258,0.00185974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001549263,"about_ca_system_score_gemma":0.001224824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001247175,"about_ca_topic_score_gemma":0.001790019,"domain_scores_codex":[0.7212859,0.2147371,0.0212996,0.01696119,0.02333046,0.002385718],"domain_scores_gemma":[0.1137343,0.8113385,0.01022657,0.05241607,0.01105338,0.001231173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.1073771,0.009737629,0.1445328,0.004066787,0.004552123,0.001514361,0.01894204,0.01322479,0.04288718,0.008359343,0.01376453,0.6310412],"study_design_scores_gemma":[0.005598198,0.03142626,0.8561891,0.001839571,0.005457981,0.002081091,0.00306615,0.01588737,0.04265715,0.01563572,0.01973262,0.0004287746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9026912,0.004358648,0.05916454,0.001802342,0.00291807,0.003142957,0.001071493,0.001436076,0.02341473],"genre_scores_gemma":[0.940062,0.0007526898,0.04781394,0.001188587,0.000726018,0.002221452,0.00121132,0.001088108,0.004935698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1830288,"threshold_uncertainty_score":0.9679605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2599093244075452,"score_gpt":0.3990953364307693,"score_spread":0.1391860120232241,"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."}}