{"id":"W4322486740","doi":"10.5539/elt.v16n3p23","title":"The Accuracy of Students' Self-Assessment-How Useful Is a Checklist in EAP Writing","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Checklist; Psychology; Autonomy; Learner autonomy; Self-assessment; Medical education; Pedagogy; Mathematics education; Language education; Medicine","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":[0.005461827,0.0001806072,0.0002606387,0.0001662464,0.0009584564,0.0006588158,0.001062436,0.000103537,0.00008419214],"category_scores_gemma":[0.001680933,0.0001528671,0.0001256781,0.0007032711,0.0001023878,0.0005302234,0.0003545183,0.0006586387,0.00002348118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002365397,"about_ca_system_score_gemma":0.0001356796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00163782,"about_ca_topic_score_gemma":0.002536071,"domain_scores_codex":[0.9968996,0.0006425203,0.0003744909,0.0003219919,0.001123433,0.000637929],"domain_scores_gemma":[0.9976676,0.001586217,0.0002339789,0.0003582657,0.00006594278,0.00008797023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000004441319,0.0000917725,0.4270626,0.0000167528,0.00004606587,0.00001280788,0.5646457,0.000001832978,0.0003100038,0.002675259,0.001656971,0.003475794],"study_design_scores_gemma":[0.0007694078,0.0000204696,0.1304865,0.00009836788,0.00002692816,2.319641e-7,0.8207961,0.00005467971,0.00004007433,0.00009178307,0.04735318,0.0002622742],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638681,0.0001769124,0.00001694843,0.0009711417,0.0005366222,0.0003910258,0.000007183925,0.0003902975,0.03364174],"genre_scores_gemma":[0.9947109,0.0001521934,0.000650629,0.0001053438,0.0007188235,0.00004055602,0.00001486728,0.00002868811,0.003577995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2965762,"threshold_uncertainty_score":0.7371768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02164002909992158,"score_gpt":0.3833339188698593,"score_spread":0.3616938897699377,"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."}}