{"id":"W4307159924","doi":"10.1002/ets2.12357","title":"Mapping<i>TOEFL</i>®<i>Essentials</i>™ Test Scores to the Canadian Language Benchmarks","year":2022,"lang":"en","type":"article","venue":"ETS Research Report Series","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Test (biology); Construct (python library); Psychology; Mathematics education; Computer science; Language assessment; English language; Test score; Natural language processing; Standardized test; Programming language","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006416193,0.00009045105,0.0001162375,0.0003120672,0.006611443,0.0003840403,0.0007106931,0.00004267483,0.009824703],"category_scores_gemma":[0.001921398,0.00007704415,0.00005149372,0.001273948,0.0004081313,0.0002053988,0.0002971046,0.0005445959,0.00008046195],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005281602,"about_ca_system_score_gemma":0.006739535,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7591901,"about_ca_topic_score_gemma":0.9640564,"domain_scores_codex":[0.9962129,0.0006559732,0.0002401745,0.0003160696,0.001832283,0.0007425827],"domain_scores_gemma":[0.9982103,0.0005616222,0.00006714972,0.0004099106,0.0003520547,0.0003989399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001593019,0.0001096059,0.1279547,0.00001697038,0.00003527167,0.001091036,0.1433097,0.00003268715,0.0006132636,0.02694616,0.6979513,0.001923415],"study_design_scores_gemma":[0.00002405048,0.00004440483,0.02741419,0.000005083078,0.000001607637,0.00004111898,0.08407428,9.840101e-7,0.00005419144,0.001237123,0.887009,0.00009402836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3261531,0.0004856556,0.000002959477,0.2413963,0.001309176,0.0009804117,0.00008441723,0.00005317849,0.4295348],"genre_scores_gemma":[0.9034816,0.00003666118,0.000108991,0.0006017162,0.000853192,0.000362953,0.000160996,0.00001227051,0.0943816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5773286,"threshold_uncertainty_score":0.9988914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09859811587093853,"score_gpt":0.4617409910682972,"score_spread":0.3631428751973587,"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."}}