{"id":"W2228140964","doi":"10.1080/02671522.2015.1086015","title":"Predictability in high-stakes examinations: students’ perspectives on a perennial assessment dilemma<sup>*</sup>","year":2015,"lang":"en","type":"article","venue":"Research Papers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; University of Oxford","keywords":"Dilemma; Certificate; Context (archaeology); Active listening; Irish; Pedagogy; Predictability; Relevance (law); Psychology; Quality (philosophy); Medical education; Engineering ethics; Public relations; Political science; Computer science; Medicine; Epistemology; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.03925771,0.000524975,0.0007713876,0.001169536,0.008810679,0.01795174,0.001924467,0.004618935,0.001822924],"category_scores_gemma":[0.06743272,0.0007072813,0.0008187988,0.0008457131,0.01690215,0.007240955,0.009883835,0.01134243,0.0005221206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005789662,"about_ca_system_score_gemma":0.005549662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003318095,"about_ca_topic_score_gemma":0.004040715,"domain_scores_codex":[0.9541366,0.03265827,0.001838427,0.00136599,0.005919533,0.004081135],"domain_scores_gemma":[0.9332166,0.04403654,0.007007268,0.002113867,0.005769463,0.007856357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00006790728,0.0001221128,0.01857365,0.0000646596,0.00001380573,0.001543304,0.9540883,0.0002863159,0.00146371,0.00629558,0.002877723,0.0146029],"study_design_scores_gemma":[0.000009668611,0.0001595482,0.004764861,0.0001105586,0.000009379866,0.0007960134,0.9674633,0.000616645,0.0007643697,0.004704118,0.02053746,0.0000640802],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632974,0.0003810928,0.002575017,0.02373184,0.0001980458,0.00004830813,0.00001467628,0.00003944521,0.009714007],"genre_scores_gemma":[0.9963303,0.0001810348,0.0006709502,0.001190957,0.00004003249,0.00002420447,0.000007068459,0.00001754794,0.001537857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03925771,"threshold_uncertainty_score":0.207617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0924787417886633,"score_gpt":0.4819874739115618,"score_spread":0.3895087321228985,"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."}}