{"id":"W3099626247","doi":"10.22215/etd/2020-14177","title":"The Government of Canada’s Second Language Evaluation, Test of Written Expression: Exploring Validity","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Government (linguistics); Test (biology); Context (archaeology); Expression (computer science); Stakeholder; Psychology; Ecological validity; Language assessment; Political science; Public relations; Mathematics education; Linguistics; Computer science; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03705103,0.0003104477,0.000453049,0.002979761,0.006968332,0.005861206,0.001796339,0.0007118912,0.0015418],"category_scores_gemma":[0.1114127,0.0002315543,0.0003174077,0.00385083,0.006538432,0.001440642,0.003558633,0.001711486,0.0002310647],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.07890192,"about_ca_system_score_gemma":0.1732947,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9541754,"about_ca_topic_score_gemma":0.9693246,"domain_scores_codex":[0.9592704,0.01346662,0.001511011,0.00137861,0.02113078,0.003242637],"domain_scores_gemma":[0.8950846,0.04275758,0.004846012,0.002731367,0.04975217,0.004828434],"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":[0.000912165,0.0006146581,0.3013328,0.001354667,0.0001151042,0.0007631596,0.164501,0.002378351,0.003193179,0.06638309,0.02252521,0.4359267],"study_design_scores_gemma":[0.0001239012,0.0008348715,0.6617525,0.001495662,0.00011182,0.0001913331,0.1974075,0.007589105,0.006502229,0.008511659,0.1152095,0.0002698239],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8177605,0.001477929,0.004726781,0.01078359,0.000237712,0.0009905173,0.0008094905,0.00008253775,0.1631311],"genre_scores_gemma":[0.9889065,0.0002869584,0.003363818,0.0004517802,0.0000126516,0.0002729495,0.0001807296,0.00001600432,0.006508654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9210981,"threshold_uncertainty_score":0.5724761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2446088050734773,"score_gpt":0.4388118233000554,"score_spread":0.1942030182265781,"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."}}