{"id":"W7128079767","doi":"10.1075/task.25007.mic","title":"Validity argument for the use of summative task-based language assessment in a language teaching program for adult immigrants","year":2025,"lang":"en","type":"article","venue":"TASK Journal on Task-Based Language Teaching and Learning","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Summative assessment; Formative assessment; Argument (complex analysis); Process (computing); Literacy; Language assessment; Authentic assessment; Dynamic assessment; Component (thermodynamics); Professional development","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006726276,0.000512626,0.0007096085,0.0006189208,0.002800232,0.0008835506,0.0003918402,0.0001392923,0.00005926115],"category_scores_gemma":[0.004406953,0.0003705709,0.0004219206,0.00009955912,0.0001811017,0.0003128055,0.00005477269,0.004586213,0.000002128047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002328185,"about_ca_system_score_gemma":0.0002161623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00330918,"about_ca_topic_score_gemma":0.001003785,"domain_scores_codex":[0.994706,0.002653678,0.0008723061,0.0005268732,0.0004976921,0.0007434501],"domain_scores_gemma":[0.9925699,0.005931588,0.0008031817,0.0003836828,0.0001697868,0.0001418708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001289256,0.001775659,0.007290555,0.001134656,0.0005129534,0.0001187394,0.4328455,0.03519903,0.004068779,0.007408258,0.002462227,0.5058944],"study_design_scores_gemma":[0.01558855,0.005022062,0.00241332,0.007218186,0.0009179667,0.00002613106,0.5656994,0.2411098,0.0009586225,0.0001049908,0.1591085,0.001832434],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700403,0.0008223499,0.02448322,0.001707977,0.0003867942,0.001434845,0.0001359135,0.0002610946,0.0007274708],"genre_scores_gemma":[0.985428,0.000009406604,0.009906173,0.001650378,0.000457025,0.0002311718,0.0001731762,0.00008045629,0.002064156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5040619,"threshold_uncertainty_score":0.9998747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03379176575737737,"score_gpt":0.3316846127173966,"score_spread":0.2978928469600192,"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."}}