{"id":"W4313892487","doi":"10.1007/978-3-031-21796-8_8","title":"None of the Above: Integrity Concerns of Standardized English Proficiency Tests","year":2023,"lang":"en","type":"book-chapter","venue":"Ethics and integrity in educational contexts","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Equity (law); English language; Coronavirus disease 2019 (COVID-19); Work (physics); Language proficiency; Test (biology); Standardized test; Political science; Psychology; Engineering ethics; Sociology; Mathematics education; Engineering; Medicine; Law","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":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003796742,0.0002059021,0.0004354922,0.0001800757,0.000301114,0.00003999734,0.0004790977,0.000789417,0.0005972503],"category_scores_gemma":[0.01695064,0.0001675474,0.0001544878,0.0001896316,0.001725024,0.00008375939,0.00009563333,0.003495356,0.000007945698],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002014546,"about_ca_system_score_gemma":0.009382768,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009576476,"about_ca_topic_score_gemma":0.01865141,"domain_scores_codex":[0.9976133,0.0003603524,0.0006682686,0.0003015754,0.0008451086,0.0002113676],"domain_scores_gemma":[0.9933991,0.003437617,0.0005322571,0.0002941149,0.002224031,0.0001129241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001624415,0.00008089576,0.001491384,0.0001135319,0.0000194956,9.72313e-8,0.1293729,3.167601e-7,0.00001153396,0.865068,0.001839102,0.001986488],"study_design_scores_gemma":[0.0008216238,0.0001065815,0.0405597,0.002789657,0.00007080119,9.478529e-7,0.02512889,0.00001074209,0.000166573,0.4114786,0.5182402,0.0006256833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03765001,0.001301809,0.000003850332,0.03467494,0.005586849,0.001185934,0.0009669203,0.00003705254,0.9185926],"genre_scores_gemma":[0.7500879,0.001306207,0.00006924426,0.0004716461,0.0008005974,0.00002338551,0.0000345882,0.00002318551,0.2471833],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7124379,"threshold_uncertainty_score":0.9992557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1820764381213399,"score_gpt":0.4948918957819943,"score_spread":0.3128154576606543,"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."}}