{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007738679,0.0003497112,0.0002719777,0.002890985,0.002590919,0.005424638,0.0007423809,0.0009549732,0.01057815],"category_scores_gemma":[0.03246785,0.0001516136,0.0001961967,0.001925168,0.01412493,0.004408696,0.006343858,0.001908531,0.001277642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00313792,"about_ca_system_score_gemma":0.004682891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004908362,"about_ca_topic_score_gemma":0.005727666,"domain_scores_codex":[0.9831072,0.01056172,0.0006730652,0.0005614783,0.004229745,0.0008668756],"domain_scores_gemma":[0.962009,0.02310075,0.003838892,0.002348983,0.005007759,0.003694591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004600948,0.0002634979,0.05456704,0.0002999878,0.00002903304,0.001244582,0.01807574,0.0005236734,0.0007371655,0.4260776,0.02584894,0.4722868],"study_design_scores_gemma":[0.0000222869,0.0002211159,0.07243595,0.001217942,0.00002653942,0.003834767,0.02950493,0.00130297,0.001727896,0.4455012,0.4441044,0.0000999003],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.09376745,0.003994661,0.01770538,0.05169607,0.0005587039,0.0001330722,0.0002455243,0.0002115569,0.8316877],"genre_scores_gemma":[0.9569528,0.003002491,0.008419938,0.005792552,0.0008069605,0.0002287474,0.0001685116,0.0001252936,0.02450276],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9974091,"threshold_uncertainty_score":0.04092652,"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."}}