{"id":"W4408274262","doi":"10.5430/wjel.v15n5p1","title":"Trustworthiness of EFL Assessment of Learning in the Age of AI: Challenges and Solutions","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Foreign Language Teaching Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Trustworthiness; Computer science; Mathematics education; Artificial intelligence; Natural language processing; Psychology; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006859311,0.00007771206,0.0003554592,0.0003985258,0.00008108913,0.00001417149,0.0003371596,0.00005051105,0.00003477723],"category_scores_gemma":[0.003328678,0.00005710612,0.0001021792,0.0004910398,0.0002763461,0.0001409032,0.00005429815,0.000573531,2.296817e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004107586,"about_ca_system_score_gemma":0.0001764365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004664882,"about_ca_topic_score_gemma":0.003856218,"domain_scores_codex":[0.9976515,0.001243314,0.0004909087,0.00008040032,0.0003708017,0.000163135],"domain_scores_gemma":[0.9982071,0.0009711019,0.0004143205,0.000140469,0.0002397636,0.00002727068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003664383,0.0002634742,0.02368047,0.0002474562,0.0001082704,0.00006565983,0.6515748,0.0005012125,0.001240788,0.2610047,0.0001313713,0.06114517],"study_design_scores_gemma":[0.001692242,0.0002429131,0.1734914,0.00146054,0.0001993141,0.00000435502,0.8047433,0.00008976729,0.0004432677,0.005277668,0.01214037,0.0002148934],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7454247,0.02191315,0.0009439398,0.0009501397,0.0004882227,0.0002090571,0.00000409258,0.00001645855,0.2300502],"genre_scores_gemma":[0.9954562,0.0004538588,0.00359367,0.00003175715,0.0001424126,0.000001467983,7.4029e-7,0.000005215268,0.0003146805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.255727,"threshold_uncertainty_score":0.3984979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02873283754247458,"score_gpt":0.3710610737244341,"score_spread":0.3423282361819596,"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."}}