{"id":"W4390795033","doi":"10.1002/9781118784235.eelt1043","title":"The Social Dimension of Language Testing","year":2024,"lang":"en","type":"other","venue":"The TESOL Encyclopedia of English Language Teaching","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Language assessment; Multilingualism; Literacy; Test (biology); Dimension (graph theory); On Language; Standardized test; Psychology; Differential item functioning; Mathematics education; Pedagogy; Linguistics; Psychometrics; Item response theory; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001115916,0.0003011213,0.0003864085,0.0001132353,0.0001596389,0.00002735199,0.0007292342,0.0002605943,0.001564908],"category_scores_gemma":[0.001369872,0.0001626947,0.0001734325,0.0002239267,0.0002276932,0.00002447523,0.0001712624,0.001068843,0.0001532514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002356368,"about_ca_system_score_gemma":0.00003789653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001313853,"about_ca_topic_score_gemma":0.00005764637,"domain_scores_codex":[0.9979596,0.0004829456,0.0004773317,0.0003670134,0.0003661077,0.0003470333],"domain_scores_gemma":[0.9974507,0.001342702,0.0005055388,0.0005900292,0.00006576303,0.000045271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002571012,0.0002711684,0.0003314405,0.0001808604,0.0003585335,0.00002530979,0.2753338,3.953555e-7,0.0001651347,0.009551333,0.6678022,0.0459541],"study_design_scores_gemma":[0.000622734,0.0002089664,0.00188879,0.0009133308,0.0004490573,0.000009792773,0.2012106,0.000005277698,0.00001910006,0.00129878,0.7927057,0.00066788],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.02053466,0.0105854,0.000009000771,0.0001527832,0.0035183,0.0003629854,0.0001080559,0.0002426275,0.9644862],"genre_scores_gemma":[0.1386566,0.00007297935,0.0007607059,0.0001668075,0.006294917,0.00008513375,0.00006467963,0.0004027189,0.8534954],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1249035,"threshold_uncertainty_score":0.9993478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02114318347531001,"score_gpt":0.3574171784129188,"score_spread":0.3362739949376087,"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."}}