{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008870041,0.00008007802,0.0001298524,0.0001044457,0.00005649224,0.00002934856,0.0009345542,0.00002628355,0.00001061818],"category_scores_gemma":[0.001075342,0.00004791571,0.00004560073,0.0002288966,0.0001244963,0.000195411,0.0001987947,0.0001684654,0.000001667199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008034785,"about_ca_system_score_gemma":0.0001877036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002538919,"about_ca_topic_score_gemma":0.000007978113,"domain_scores_codex":[0.9987934,0.0001030931,0.0003310445,0.0001657519,0.0005236432,0.00008309851],"domain_scores_gemma":[0.9967484,0.0007013918,0.0002884133,0.0002756665,0.001976605,0.00000947449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[2.688294e-7,0.0002358407,0.406525,0.00002214096,0.00004260245,3.03867e-8,0.007637247,0.00001541519,0.0001743766,0.5824999,0.001857594,0.0009896309],"study_design_scores_gemma":[0.0001607046,0.00004935586,0.8973961,0.0001535919,0.000008699723,0.000001878194,0.02614008,0.0007727846,0.0009290415,0.07088267,0.003415434,0.00008965583],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962124,0.00009533341,0.0007491527,0.02885487,0.002969768,0.000188155,0.000002137658,0.00001591367,0.005000656],"genre_scores_gemma":[0.9943709,0.00003914008,0.004620425,0.0005077978,0.0001044126,0.00009576599,0.00000529708,0.000002385342,0.0002539272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5116172,"threshold_uncertainty_score":0.1953946,"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."}}