{"id":"W3117672137","doi":"10.3968/11905","title":"Backwash in Higher Education: Calibrating assessment and swinging the pendulum From Summative Assessment","year":2020,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Summative assessment; Phenomenon; Affect (linguistics); Higher education; Pedagogy; Mathematics education; Sociology; Psychology; Formative assessment; Epistemology; Philosophy; Political science; Law","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009045666,0.0001140838,0.0001454947,0.00007987506,0.002189597,0.0006752152,0.0006086098,0.00006144213,0.000816129],"category_scores_gemma":[0.00006094928,0.0001030074,0.00003112887,0.001230599,0.0008304195,0.0006188083,0.0001050755,0.0002602326,0.000009440249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074588,"about_ca_system_score_gemma":0.004898382,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.085085,"about_ca_topic_score_gemma":0.07411961,"domain_scores_codex":[0.9980732,0.0001881843,0.00018838,0.0003700581,0.000643146,0.0005370824],"domain_scores_gemma":[0.9991284,0.0001359546,0.00008874485,0.00008675424,0.00008379058,0.0004763498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001160628,0.0000216699,0.6700149,0.000003944785,0.000009604328,0.000006033014,0.06086159,9.708933e-7,0.0003487292,0.25813,0.003064563,0.007536812],"study_design_scores_gemma":[0.0001806407,0.00001271628,0.8173305,0.0000209652,0.00001064368,6.147148e-8,0.13443,0.0002176776,0.000005402712,0.001217432,0.04635072,0.0002231675],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2543139,0.00009514691,0.00002612827,0.07842728,0.0009318694,0.0004735399,0.00001680295,0.00003658977,0.6656787],"genre_scores_gemma":[0.9940386,0.0000119179,0.0005907728,0.004037057,0.0008887806,0.00002801025,0.000004866246,0.000007331623,0.000392697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7397246,"threshold_uncertainty_score":0.9991094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05916599259504846,"score_gpt":0.3728504895420151,"score_spread":0.3136844969469667,"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."}}