{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008332319,0.0004674018,0.0005044898,0.0006667385,0.0007235084,0.002508841,0.0007805378,0.0005005579,0.002667523],"category_scores_gemma":[0.0452657,0.0001860754,0.0002680002,0.0004223103,0.0008491271,0.001572255,0.001415186,0.000700113,0.0006097723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004110234,"about_ca_system_score_gemma":0.001051148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004609026,"about_ca_topic_score_gemma":0.0008134026,"domain_scores_codex":[0.990316,0.006399368,0.0003571398,0.0006029367,0.001996589,0.0003280806],"domain_scores_gemma":[0.9554349,0.03428419,0.003599046,0.002034765,0.003147001,0.001500264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00255828,0.007379332,0.08995279,0.001975042,0.0001806397,0.001497772,0.1407902,0.001531525,0.07263853,0.001598596,0.001700299,0.6781971],"study_design_scores_gemma":[0.0004625439,0.06471466,0.6177897,0.00132607,0.0007094048,0.002293647,0.1506299,0.01076497,0.1025221,0.003498668,0.0449064,0.0003818567],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923792,0.0001363989,0.002897356,0.0001574963,0.00002718359,0.0001214665,0.00001852531,0.00005702395,0.004205311],"genre_scores_gemma":[0.99282,0.0001253388,0.004902743,0.00006227215,0.00002543036,0.0001020163,0.0000168584,0.00001899247,0.001926371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008332319,"threshold_uncertainty_score":0.04406601,"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."}}