{"id":"W2752915344","doi":"","title":"A Methodology for Generating Items in Three or More Languages Using Automated Processes","year":2015,"lang":"en","type":"article","venue":"","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Context (archaeology); Key (lock); Artificial intelligence; Process (computing); Sample (material); Test (biology); Quality (philosophy); Programming language","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":[0.0004788392,0.00006376192,0.0001037347,0.00009854071,0.00004297373,0.00003228336,0.0003025837,0.00006467095,0.000003285716],"category_scores_gemma":[0.0005491927,0.0000462362,0.000009887574,0.0003704321,0.00002420729,0.000181229,0.00008230131,0.00005116237,0.000001367572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003764576,"about_ca_system_score_gemma":0.0004807845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008660638,"about_ca_topic_score_gemma":0.000318367,"domain_scores_codex":[0.9994228,0.0000374385,0.000132731,0.0001898197,0.00006837668,0.0001488206],"domain_scores_gemma":[0.9993618,0.0002988349,0.00004833766,0.0001462601,0.0001169269,0.00002791166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009454201,0.001104499,0.07833871,0.0005895274,0.0001730943,0.0001190998,0.01785847,0.02715526,0.05400275,0.7390813,0.01073027,0.0707525],"study_design_scores_gemma":[0.0004076666,0.00009044766,0.0007382734,0.00002652984,0.000003936313,0.00005193679,0.001961495,0.9680747,0.01556789,0.012623,0.0003011104,0.0001530351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2757633,0.0001377875,0.7213646,0.001990871,0.0001129318,0.000146803,6.563217e-7,0.0003721337,0.000110926],"genre_scores_gemma":[0.2131852,7.416571e-7,0.7863592,0.0002438103,0.0000358851,0.00005213073,0.000001797957,0.000003338037,0.0001178843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9409194,"threshold_uncertainty_score":0.1885458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3135886522604918,"score_gpt":0.4830725199177633,"score_spread":0.1694838676572715,"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."}}