{"id":"W2114045556","doi":"10.1017/s0267190505000115","title":"TRENDS IN ASSESSMENT SCALES AND CRITERION-REFERENCED LANGUAGE ASSESSMENT","year":2005,"lang":"en","type":"article","venue":"Annual Review of Applied Linguistics","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Trait; Computer science; Scale (ratio); Task (project management); Benchmark (surveying); Language assessment; Foreign language; Test (biology); Cognitive psychology; Psychology; Natural language processing; Geography; Mathematics education; Engineering; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09179102,0.001001523,0.001692253,0.01329261,0.001965596,0.009588391,0.006074619,0.003543902,0.00292812],"category_scores_gemma":[0.1531328,0.0008084679,0.001164615,0.01685818,0.01032374,0.009882514,0.004902434,0.008876228,0.001935444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03103669,"about_ca_system_score_gemma":0.03122549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0525746,"about_ca_topic_score_gemma":0.03172955,"domain_scores_codex":[0.8585213,0.03664769,0.01127379,0.01042153,0.0814166,0.001719092],"domain_scores_gemma":[0.7882298,0.07606462,0.008471338,0.009630846,0.112598,0.005005397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000102858,0.0001991725,0.009495406,0.002426774,0.00006036396,0.00005828522,0.004290567,0.001376176,0.001215584,0.3938115,0.03012566,0.5568377],"study_design_scores_gemma":[0.00005133681,0.0004347557,0.05896005,0.005542343,0.00006578783,0.0008267944,0.005055978,0.00712915,0.00218069,0.1359679,0.7835346,0.0002505563],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0404217,0.2842284,0.279447,0.1342857,0.004995832,0.001067005,0.001508063,0.003420407,0.2506259],"genre_scores_gemma":[0.2934201,0.140018,0.5044286,0.01958882,0.004608669,0.003031032,0.002837221,0.001799415,0.03026814],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.09179102,"threshold_uncertainty_score":0.4854431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02217392143505261,"score_gpt":0.3520408991979247,"score_spread":0.3298669777628721,"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."}}