{"id":"W4393899036","doi":"10.5430/wjel.v14n4p215","title":"Beyond the Red Pen: Exploring the Impact of Language Peer Assessment Technology on the ESL/EFL Writers’ Performance","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Peer assessment; Linguistics; Mathematics education; Psychology; Philosophy","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":[0.00313685,0.0001550848,0.0002247454,0.0002711799,0.0003900035,0.0002450561,0.0009928922,0.00004655904,0.0005412725],"category_scores_gemma":[0.0005988982,0.00006734383,0.0002834806,0.001036862,0.0002894893,0.0003445502,0.0001050227,0.0008583126,0.000005523612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001874051,"about_ca_system_score_gemma":0.0001837882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001021522,"about_ca_topic_score_gemma":0.0001781419,"domain_scores_codex":[0.9980235,0.0002447048,0.0003606847,0.0001320403,0.0009161413,0.0003229645],"domain_scores_gemma":[0.9982555,0.0008384375,0.0002356534,0.0003217674,0.0002962544,0.00005239547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001142769,0.0002283628,0.02871564,0.00004158186,0.0008549166,0.0002070204,0.805504,0.0001342621,0.002094181,0.05458053,0.07119238,0.03633289],"study_design_scores_gemma":[0.0008183127,0.0006387442,0.05409625,0.0006186006,0.0002483475,0.00001568021,0.8798488,0.0001552183,0.001304247,0.001262086,0.06059388,0.0003998573],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9106153,0.001320301,0.000004718623,0.008235364,0.001412396,0.0002152883,0.000004959885,0.00004117778,0.07815044],"genre_scores_gemma":[0.9945835,0.0002205404,0.00007521323,0.0001060994,0.00163121,0.00001506859,0.000001062417,0.00001789467,0.003349346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08396821,"threshold_uncertainty_score":0.5926554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02639932192839465,"score_gpt":0.3478451427577096,"score_spread":0.3214458208293149,"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."}}