{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007214264,0.0001390338,0.0001884478,0.0006237153,0.0003508157,0.0002899616,0.0006154515,0.0001317394,0.0003355278],"category_scores_gemma":[0.002520531,0.0001384133,0.00004078931,0.001244941,0.0004523927,0.0003950531,0.0001100392,0.0005886825,0.00003831405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003797536,"about_ca_system_score_gemma":0.002657207,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008516969,"about_ca_topic_score_gemma":0.003934582,"domain_scores_codex":[0.9940862,0.001944818,0.0003054509,0.0005226819,0.002556225,0.0005846326],"domain_scores_gemma":[0.9981534,0.0007582898,0.00005636649,0.0003103954,0.0004938803,0.0002276121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004399242,0.002641999,0.7887654,0.000009997064,0.00001070928,0.000001669352,0.1790244,0.00006969633,0.00001905955,0.02202815,0.0007749708,0.006610039],"study_design_scores_gemma":[0.0004874464,0.0001212182,0.5611221,0.00004626414,0.000002316007,6.69636e-8,0.4342732,0.00005856068,0.000001160489,0.0008363239,0.00296475,0.00008662038],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9088344,0.0001091355,0.000001799259,0.002341367,0.0002977286,0.001092525,0.000004198726,0.00003490034,0.08728397],"genre_scores_gemma":[0.9963167,0.0003204727,0.000355755,0.00002868847,0.0005063934,0.0005797484,0.00002455022,0.00001339421,0.0018543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2552488,"threshold_uncertainty_score":0.9980854,"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."}}