{"id":"W7100226999","doi":"","title":"Paper Presented at the Symposium entitled “Improving Large-Scale Assessment in Education ” at the Annual Meeting of the Canadian Society for the Study of Education","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Research council; Standardized test; Educational assessment; Government (linguistics); National education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001518333,0.00008995721,0.0001037099,0.00002236037,0.001540647,0.0001000748,0.0005505684,0.00005416626,0.0006213435],"category_scores_gemma":[0.00006697476,0.0000402926,0.0001250439,0.0003068166,0.0001653838,0.0001887555,0.0001900203,0.0001141122,0.000004055982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005328787,"about_ca_system_score_gemma":0.001342315,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5558246,"about_ca_topic_score_gemma":0.9472316,"domain_scores_codex":[0.9985545,0.0002584711,0.0002674216,0.0001670853,0.000485609,0.0002668683],"domain_scores_gemma":[0.9986916,0.0004389462,0.0002130525,0.0003240916,0.000291275,0.00004102943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000007291856,0.0008599695,0.6965773,0.00002181522,0.0001102435,7.466134e-9,0.216033,0.0000483813,0.001672943,0.002151683,0.07995661,0.002560785],"study_design_scores_gemma":[0.0002517806,0.00002529546,0.3865024,0.00001312658,0.00006018928,5.030954e-8,0.5960877,0.0003146171,0.00009112057,0.00006844934,0.01652384,0.00006146247],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390919,0.0001169282,0.000005961282,0.02339012,0.0007824681,0.003695367,0.000008620284,0.000006890821,0.03290175],"genre_scores_gemma":[0.9750658,0.00002354416,0.00005445776,0.0004212852,0.0001486603,0.0005180826,0.000005577314,0.00000803801,0.02375459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.391407,"threshold_uncertainty_score":0.9997592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01147772045678067,"score_gpt":0.323893062274081,"score_spread":0.3124153418173003,"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."}}