{"id":"W2989633901","doi":"10.5539/ies.v12n12p55","title":"Investigating the Validity of Different Peer Groupings in the Assessment of English Writings","year":2019,"lang":"en","type":"article","venue":"International Education Studies","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Guangdong University of Foreign Studies","keywords":"Peer feedback; Peer assessment; Psychology; Peer evaluation; Promotion (chess); Homogeneous; Mathematics education; Quality (philosophy); Test validity; Construct validity; Higher education; Psychometrics; Developmental psychology; Mathematics","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":[0.07199797,0.0004462352,0.0006599111,0.003280731,0.001176803,0.002293732,0.00121149,0.0009545098,0.0008269224],"category_scores_gemma":[0.2885738,0.0003097245,0.001077423,0.001576874,0.002746568,0.003266173,0.003415285,0.0009477685,0.000362466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009031477,"about_ca_system_score_gemma":0.001360916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001675819,"about_ca_topic_score_gemma":0.002016638,"domain_scores_codex":[0.9203019,0.04475438,0.005881724,0.004467385,0.02295046,0.00164417],"domain_scores_gemma":[0.6421717,0.2555728,0.03875229,0.02369274,0.03431807,0.005492356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00154998,0.0005968235,0.8827267,0.0002278203,0.00052617,0.0001053789,0.02414499,0.001009157,0.00260513,0.0006625357,0.0002541041,0.08559126],"study_design_scores_gemma":[0.00009765953,0.003207399,0.9691102,0.0002758122,0.0002607577,0.000259345,0.01424239,0.005816385,0.00369734,0.00120085,0.001746054,0.00008582196],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993239,0.0002159335,0.002267553,0.00009708645,0.00004526403,0.0001905156,0.00002733995,0.00001792367,0.003899401],"genre_scores_gemma":[0.9983883,0.00004909023,0.001142503,0.00001213545,0.00001397702,0.00007089489,0.00004279464,0.000009176812,0.0002712376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07199797,"threshold_uncertainty_score":0.3807662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07087660242822855,"score_gpt":0.4062094524306231,"score_spread":0.3353328500023945,"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."}}