{"id":"W2072296938","doi":"10.1080/10627190802394222","title":"Validity Issues in Assessing English Language Learners' Language Proficiency","year":2008,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Memorial University of Newfoundland","keywords":"Accountability; Legislation; Language proficiency; Language assessment; Psychology; English language; Pedagogy; Medical education; Mathematics education; Political science; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4755363,0.0007453884,0.001628255,0.007086383,0.006843224,0.008754864,0.003277047,0.002809954,0.001533514],"category_scores_gemma":[0.6634406,0.0008835891,0.00195967,0.006058418,0.02186871,0.009952812,0.008223538,0.004860862,0.0005631007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00895578,"about_ca_system_score_gemma":0.02553042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01127853,"about_ca_topic_score_gemma":0.01190938,"domain_scores_codex":[0.4212688,0.421712,0.04943635,0.01275552,0.09128568,0.003541731],"domain_scores_gemma":[0.239348,0.6323883,0.02509948,0.02553212,0.07563836,0.00199378],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004294566,0.0004156962,0.2184798,0.005036267,0.000792253,0.0004807914,0.05727706,0.002346057,0.001710829,0.3053556,0.01209895,0.3955773],"study_design_scores_gemma":[0.0003479783,0.00174166,0.210841,0.02288405,0.0009086266,0.001807904,0.06677267,0.02033404,0.01107296,0.5300572,0.1327744,0.0004575288],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2105878,0.02595357,0.4274227,0.1304906,0.005109836,0.008753577,0.0009393753,0.0004330454,0.1903095],"genre_scores_gemma":[0.7472276,0.004381286,0.2241248,0.01183519,0.001261517,0.007369042,0.0004529495,0.0002416676,0.003105988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4755363,"threshold_uncertainty_score":0.6467571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06769468706590388,"score_gpt":0.4642791324549266,"score_spread":0.3965844453890227,"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."}}