{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007129246,0.00009003902,0.0003490303,0.00003042654,0.00006310609,0.00002035123,0.0001035849,0.00004711088,0.0003290685],"category_scores_gemma":[0.0009319531,0.00008825362,0.0000277865,0.0001671825,0.0001806076,0.00001304262,0.00005260376,0.0001309802,0.000001491394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001852967,"about_ca_system_score_gemma":0.00008135935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006386395,"about_ca_topic_score_gemma":0.00006595807,"domain_scores_codex":[0.9989424,0.00004469359,0.0003860942,0.0001577654,0.0003354766,0.0001335759],"domain_scores_gemma":[0.9993304,0.0001829783,0.0001920302,0.00007827915,0.000142439,0.00007387624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001654992,0.0002674828,0.05673374,0.01372143,0.0001043077,0.00001719382,0.03554767,0.000003206319,0.001876603,0.8777627,0.006245592,0.007703528],"study_design_scores_gemma":[0.005581974,0.0004243424,0.4063787,0.01539138,0.001032021,0.000001258706,0.1497046,0.0006740054,0.0007140205,0.007632767,0.4104826,0.001982332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4397283,0.01268575,0.0000402129,0.001796297,0.000184531,0.001128357,0.0001044863,0.0000410279,0.5442911],"genre_scores_gemma":[0.9924665,0.004737506,0.001992011,0.0004020122,0.0002469638,0.00001189185,0.0000203678,0.000008090163,0.0001146392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8701299,"threshold_uncertainty_score":0.3603069,"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."}}