{"id":"W2910311397","doi":"10.24908/pceea.v0i0.13048","title":"What Makes a Good Assessment? Assessments for Learning","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Engineering Education and Curriculum Development","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Expectancy theory; Framing (construction); Scope (computer science); Term (time); Context (archaeology); Computer science; Psychology; Engineering; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0004377941,0.0002013429,0.0001799495,0.000292413,0.0002189272,0.0002901044,0.0002980093,0.0001562419,0.00004867153],"category_scores_gemma":[0.0003094522,0.000209817,0.00009217551,0.0005383025,0.00001536247,0.0004832679,0.00001764296,0.0002527675,0.00001290851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002608521,"about_ca_system_score_gemma":0.000576845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002626203,"about_ca_topic_score_gemma":0.0009183789,"domain_scores_codex":[0.9987755,0.000004586034,0.0003196605,0.0001917054,0.0003037087,0.0004048829],"domain_scores_gemma":[0.9987646,0.00005046756,0.0001644974,0.00009936395,0.0007169696,0.0002041174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001036338,0.000486658,0.2934069,0.00375293,0.001773334,1.924466e-7,0.01096553,0.03460149,0.03380978,0.08362718,0.5034108,0.03415484],"study_design_scores_gemma":[0.0006489597,0.0000948981,0.2544555,0.0007994837,0.0001401475,0.00000681633,0.002675703,0.07545579,0.01056975,0.000435016,0.6536627,0.001055258],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8808367,0.0006978337,0.003417354,0.008413469,0.05063324,0.003222724,0.00006229828,0.001757708,0.05095872],"genre_scores_gemma":[0.9859076,0.00004118585,0.007326615,0.0001441179,0.0004785087,0.0002729949,0.00002287096,0.00007267391,0.005733484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1502519,"threshold_uncertainty_score":0.8556088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005712140260805949,"score_gpt":0.2447546381704173,"score_spread":0.2390424979096114,"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."}}