{"id":"W4416807726","doi":"10.1016/j.asw.2025.100992","title":"How reliable and valid is peer evaluation in adolescents’ L2 argumentative writing?","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of British Columbia","keywords":"Argumentative; Grammar; Peer assessment; Reliability (semiconductor); Literacy; Peer feedback; Second language writing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005120745,0.0001432381,0.0001988266,0.0002467512,0.001081354,0.001597581,0.0001374504,0.0001312074,0.00002024938],"category_scores_gemma":[0.00170432,0.0001733319,0.0000408049,0.0006286618,0.0001636233,0.0008346878,0.00005157641,0.000294586,0.000003332742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003493663,"about_ca_system_score_gemma":0.0004583799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00124656,"about_ca_topic_score_gemma":0.0003184175,"domain_scores_codex":[0.9977475,0.0003663024,0.0003297017,0.000424791,0.0006738662,0.0004578664],"domain_scores_gemma":[0.9988355,0.0002414603,0.0001702668,0.000137849,0.0005429285,0.00007196763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000007408028,0.0001625137,0.858923,0.0002541493,0.00001963996,0.000004295859,0.02267268,0.000009535001,0.001098842,0.01052733,0.002582853,0.1037377],"study_design_scores_gemma":[0.002372103,0.00003372152,0.366957,0.0103728,0.000151118,0.00000415052,0.5915356,0.003631499,0.00249535,0.01417855,0.007510998,0.0007570799],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9203585,0.0006612993,0.000245763,0.01791026,0.0003370977,0.000355248,0.000002123711,0.0001102821,0.06001944],"genre_scores_gemma":[0.9947581,0.00004139585,0.001880695,0.0006838376,0.000323734,0.00004570048,0.00001046799,0.00001483468,0.002241242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5688629,"threshold_uncertainty_score":0.9994389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05378053516253805,"score_gpt":0.4197787474552024,"score_spread":0.3659982122926643,"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."}}