{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006201954,0.0001566243,0.000382272,0.0001222676,0.0001038121,0.00004753915,0.0001173461,0.00003511481,0.0005114308],"category_scores_gemma":[0.0001626759,0.0001316255,0.00005145615,0.0000512173,0.0001053196,0.00002295641,0.00005705619,0.000315775,0.000008283292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003744997,"about_ca_system_score_gemma":0.00003120019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007975375,"about_ca_topic_score_gemma":0.0001906477,"domain_scores_codex":[0.9989054,0.00005302204,0.0004451521,0.0002019856,0.0002095417,0.000184932],"domain_scores_gemma":[0.9993895,0.0001124917,0.0001624027,0.0001769743,0.0001047434,0.00005383044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000680579,0.0001535621,0.0001888096,0.001800371,0.00002342428,0.000004826783,0.01882338,0.00001070603,0.00002800494,0.6396967,0.002849175,0.3364143],"study_design_scores_gemma":[0.0002908352,0.00007957695,0.001756789,0.002145831,0.00005192142,6.618352e-7,0.004674288,0.0001841306,0.000009745285,0.0003062966,0.9902695,0.00023038],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02195186,0.01351565,0.000041207,0.0004656718,0.0002712149,0.0002218338,0.00009325853,0.00007518249,0.9633641],"genre_scores_gemma":[0.9895317,0.003684128,0.004303109,0.0007337274,0.0007709816,0.00001732742,0.00008020361,0.00001723123,0.000861622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9874204,"threshold_uncertainty_score":0.5599809,"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."}}