{"id":"W2943526579","doi":"","title":"Exploring the use of formative assessment for measuring and improving student learning progression","year":2018,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Educational Research and Pedagogy","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Remedial education; Mathematics education; Psychology; Class (philosophy); Test (biology); Computer science; Artificial intelligence","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":[0.0009840984,0.00007239322,0.0001040038,0.0000360645,0.0007664912,0.0001005606,0.0006788978,0.00001824995,0.00000166857],"category_scores_gemma":[0.0002941806,0.00004062696,0.00008681422,0.0001454724,0.0001734984,0.0003775049,0.0001331719,0.0001074599,1.063711e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238696,"about_ca_system_score_gemma":0.002326435,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01833993,"about_ca_topic_score_gemma":0.02182655,"domain_scores_codex":[0.9991086,0.0000764236,0.0001995556,0.0001356163,0.0002987551,0.0001811156],"domain_scores_gemma":[0.9977955,0.0006130879,0.0002654161,0.0003229718,0.0009403827,0.0000625947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003634345,0.0005921707,0.03119272,0.0003008229,0.0004542235,1.139483e-8,0.3866582,0.0002346737,0.00233959,0.03626323,0.002768903,0.5391592],"study_design_scores_gemma":[0.001222831,0.002672398,0.6654142,0.0004829976,0.0001823006,0.000002126278,0.2608079,0.05151348,0.006155958,0.003269073,0.007938231,0.0003385217],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834455,0.00007044952,0.01117486,0.002845304,0.000533558,0.001867509,0.000009306404,0.000003710122,0.0000498651],"genre_scores_gemma":[0.9936997,0.00001924626,0.005717422,0.00003616827,0.00006690226,0.0003068452,0.000001639786,0.000004621892,0.000147442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6342215,"threshold_uncertainty_score":0.9960226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2685258943541691,"score_gpt":0.4035551666279897,"score_spread":0.1350292722738206,"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."}}