{"id":"W3158855527","doi":"10.1007/s40979-021-00077-7","title":"Ungrading: why rating students undermines learning (and what to do instead)","year":2021,"lang":"en","type":"article","venue":"International Journal for Educational Integrity","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":167,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Agencia Nacional de Investigación y Desarrollo","keywords":"Psychology; Mathematics education; Rating system; Economics","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":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001880583,0.0001412009,0.000153602,0.0001942876,0.00112469,0.004315649,0.0005571741,0.00009914251,0.00104116],"category_scores_gemma":[0.01000934,0.0001491736,0.0001028224,0.0002799465,0.0001069456,0.00224962,0.000105277,0.0007244957,0.00005389042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005258317,"about_ca_system_score_gemma":0.001604542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002804431,"about_ca_topic_score_gemma":0.0004332213,"domain_scores_codex":[0.9974508,0.000448344,0.0004026077,0.0003152334,0.001110818,0.000272247],"domain_scores_gemma":[0.9946525,0.001919666,0.0003089128,0.00007932714,0.00271025,0.0003293102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001276812,0.001046542,0.5991418,0.00002671711,0.0005730718,0.00001963731,0.1004696,0.0002543791,0.0006759422,0.2054961,0.03640333,0.05576513],"study_design_scores_gemma":[0.0002960412,0.00003538409,0.0158474,0.0002165399,0.00002431441,0.0001154862,0.06999995,0.0000177329,0.0001162841,0.01243882,0.9006928,0.0001992832],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7209265,0.001171371,0.001339743,0.2582167,0.01493165,0.0002408358,0.000005269308,0.00003664008,0.003131326],"genre_scores_gemma":[0.965339,0.001046626,0.007597919,0.00280102,0.00391306,0.00005529699,0.00003641452,0.00002353012,0.01918712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8642895,"threshold_uncertainty_score":0.999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06699258393408913,"score_gpt":0.5038929804987623,"score_spread":0.4369003965646732,"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."}}