{"id":"W3096667251","doi":"10.1075/itl.20006.rez","title":"Peer and teacher assessment of second-language writing in high- and low-stakes conditions","year":2020,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Psychology; Rasch model; Peer assessment; Writing assessment; Consistency (knowledge bases); Inter-rater reliability; Variation (astronomy); Rating scale; Mathematics education; English language; Peer evaluation; Medical education; Developmental psychology; Medicine; Higher education; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009641112,0.0003320584,0.0007697241,0.001617785,0.0008135678,0.001534916,0.0004985692,0.000412078,0.001608034],"category_scores_gemma":[0.05741796,0.0001926115,0.0002727801,0.0004819273,0.0009192874,0.0008307323,0.002304101,0.0005473731,0.0003651318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007766527,"about_ca_system_score_gemma":0.0007376032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001502604,"about_ca_topic_score_gemma":0.002912761,"domain_scores_codex":[0.9878128,0.006139239,0.001013178,0.0009144512,0.003701222,0.0004191817],"domain_scores_gemma":[0.9465153,0.02472812,0.01130914,0.002641218,0.01077687,0.00402937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001792587,0.001424915,0.8560204,0.0002826329,0.0001537846,0.0008588213,0.03803905,0.0004608747,0.01529967,0.0001593947,0.0007286525,0.08477935],"study_design_scores_gemma":[0.00007593536,0.002526759,0.9707347,0.00007800532,0.00004891916,0.0007516702,0.01684684,0.001186302,0.006488435,0.0002325613,0.0009789215,0.00005089893],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992231,0.00004143341,0.0001076856,0.00001540934,0.000004620303,0.00001365653,0.0000114485,0.000006281669,0.0005762425],"genre_scores_gemma":[0.9995598,0.00001932702,0.0001534995,0.000005559268,0.000003893466,0.00001711025,0.00001799313,0.000002367895,0.0002204384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009641112,"threshold_uncertainty_score":0.05098766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02505794243865444,"score_gpt":0.3707478996727184,"score_spread":0.3456899572340639,"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."}}