{"id":"W4408741152","doi":"10.1080/13562517.2025.2468598","title":"The multiplicity of authenticity in higher education assessment","year":2025,"lang":"en","type":"article","venue":"Teaching in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Higher education; Mathematics education; Multiplicity (mathematics); Pedagogy; Psychology; Sociology; Mathematics; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015672,0.00009456858,0.0001323668,0.0001835949,0.0003559917,0.0000884231,0.0003364529,0.00008663074,0.0001722135],"category_scores_gemma":[0.00007036819,0.00008181955,0.00004143212,0.0004409127,0.0001018237,0.0001895822,0.00004954379,0.000308463,0.000004503434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006394504,"about_ca_system_score_gemma":0.0008987605,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009247896,"about_ca_topic_score_gemma":0.002807048,"domain_scores_codex":[0.9984651,0.0004971493,0.0003353644,0.0001975072,0.0002883634,0.0002164716],"domain_scores_gemma":[0.9992002,0.000354823,0.0001445443,0.000216541,0.00005316762,0.00003069382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005630647,0.000680553,0.6410243,0.00001247843,0.000006668548,2.526981e-8,0.006097639,0.000004604747,0.00009770173,0.3419157,0.001802378,0.008352312],"study_design_scores_gemma":[0.0001564876,0.000006448033,0.9327933,0.00009272437,0.00001037047,1.075719e-8,0.004821569,0.00001900819,0.000007128753,0.008869981,0.05314847,0.00007453882],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7898162,0.0002067743,0.00001079015,0.01229605,0.004205088,0.0004095352,5.002966e-7,0.00002705546,0.193028],"genre_scores_gemma":[0.9529001,0.00002853726,0.0005044246,0.0002216548,0.0002385222,0.0001152526,0.000007659967,0.00000558616,0.04597829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3330457,"threshold_uncertainty_score":0.9973496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04774720581073633,"score_gpt":0.4288700821852897,"score_spread":0.3811228763745534,"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."}}