{"id":"W1797460826","doi":"","title":"Putting Rubrics to the Test: The Effect of Rubric-Referenced Peer Assessment on EFL Learners’ Evaluation of Speaking","year":2013,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Formative assessment; Peer assessment; Psychology; Presupposition; Test (biology); Mathematics education; Peer feedback; Pedagogy; Computer science; Linguistics","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":[0.01768866,0.0009872932,0.0009965911,0.001431594,0.001034724,0.001454393,0.001468545,0.0006664571,0.001698517],"category_scores_gemma":[0.1298854,0.000320764,0.0007100556,0.000576479,0.001071967,0.001433567,0.002363052,0.001053833,0.0004994932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000545755,"about_ca_system_score_gemma":0.0009656828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009448125,"about_ca_topic_score_gemma":0.001712319,"domain_scores_codex":[0.9717748,0.01829383,0.001595862,0.001578295,0.00618876,0.0005684689],"domain_scores_gemma":[0.9077905,0.06082594,0.009251787,0.006133833,0.0131468,0.002851115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0026244,0.005268653,0.08420882,0.00138633,0.0003276361,0.0007988261,0.0646337,0.00219353,0.07218933,0.0007087936,0.001911679,0.7637482],"study_design_scores_gemma":[0.000662111,0.05794692,0.649276,0.001813496,0.001348796,0.004727638,0.09998529,0.0268474,0.1292644,0.003414704,0.02352916,0.001184077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861699,0.0003613805,0.007884146,0.000171388,0.00008579438,0.0004695635,0.00002264483,0.0002898376,0.004545238],"genre_scores_gemma":[0.9760582,0.0002467051,0.02166935,0.00009497748,0.00004292225,0.0002839544,0.00004507549,0.00005026118,0.001508595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01768866,"threshold_uncertainty_score":0.0935477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08647179667909898,"score_gpt":0.4307727206229517,"score_spread":0.3443009239438527,"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."}}