{"id":"W6996612579","doi":"","title":"A standard setting study to establish concordance between the Pearson Test of English Academic (PTE A) and the Canadian Language Benchmarks (CLB)","year":2017,"lang":"en","type":"book","venue":"ePrints Soton (University of Southampton)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Triacetin; Durvalumab; Emperipolesis","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01642986,0.0003220271,0.001128675,0.0007091752,0.001197017,0.0002172178,0.003971986,0.0003053571,0.0004999221],"category_scores_gemma":[0.08230607,0.0002314997,0.0002282328,0.0005965071,0.001266569,0.0002400721,0.001469554,0.001337296,0.00001953018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002121473,"about_ca_system_score_gemma":0.0008818077,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05276419,"about_ca_topic_score_gemma":0.06004457,"domain_scores_codex":[0.9957758,0.0007063919,0.0006052413,0.0008479092,0.001599843,0.0004648825],"domain_scores_gemma":[0.9725175,0.02264673,0.001749065,0.001727044,0.0010355,0.0003241149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002113973,0.00002712125,0.7148045,0.00005397918,0.0002450197,0.00004732244,0.1674007,0.00001523871,0.000004247455,0.0003455004,0.02791704,0.08892792],"study_design_scores_gemma":[0.003322441,0.0004095338,0.6489483,0.0006199988,0.000344958,0.000003556646,0.2273272,0.00006461477,0.00001370489,0.008428426,0.109786,0.0007313156],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6876767,0.0004017344,0.0004905672,0.001106944,0.0007204249,0.002291755,0.001220771,0.00004225409,0.3060489],"genre_scores_gemma":[0.9349315,0.00004986961,0.001671838,0.00008049567,0.0003072848,0.000001687247,0.00001671757,0.0000261232,0.06291451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2472548,"threshold_uncertainty_score":0.9571072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1172114437795707,"score_gpt":0.3592911943946659,"score_spread":0.2420797506150952,"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."}}