{"id":"W2513214169","doi":"10.22329/celt.v9i0.4435","title":"Bento and Buffet: Two Approaches to Flexible Summative Assessment","year":2016,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Summative assessment; Weighting; Dilemma; Workload; Formative assessment; Variety (cybernetics); Mathematics education; Value (mathematics); Computer science; Psychology; Artificial intelligence; Mathematics; Machine learning","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.004444642,0.0001552107,0.0001972623,0.0002141282,0.002589352,0.0003257139,0.0001334249,0.00007398425,0.0001097015],"category_scores_gemma":[0.004419359,0.0001203488,0.00002769125,0.0001644271,0.0001206418,0.000388841,0.00008901276,0.0005371986,0.00002109045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001893988,"about_ca_system_score_gemma":0.0001365824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001156522,"about_ca_topic_score_gemma":0.0004630692,"domain_scores_codex":[0.9962764,0.00232931,0.0001897574,0.0004085239,0.0004744138,0.0003216382],"domain_scores_gemma":[0.9972953,0.002170231,0.0001653287,0.0001108126,0.00004932515,0.0002090219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001113033,0.0001815138,0.1127095,0.00002608033,0.0001134727,0.000004064783,0.06950805,0.0003743092,0.00095232,0.4487138,0.001528365,0.3657772],"study_design_scores_gemma":[0.006103044,0.001970736,0.1514232,0.001302513,0.0002402193,0.00001226614,0.06700446,0.005118379,0.0004802285,0.01660242,0.7477205,0.002022009],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6509278,0.00009421579,0.006637106,0.02607255,0.0001548847,0.0004495629,0.00000306635,0.0003786163,0.3152822],"genre_scores_gemma":[0.9775043,0.00004522088,0.005115026,0.0001260172,0.00013135,0.00003929724,0.000002426838,0.00001972775,0.01701661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7461922,"threshold_uncertainty_score":0.9987091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1958890377832956,"score_gpt":0.4287281324311639,"score_spread":0.2328390946478683,"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."}}