{"id":"W4221082314","doi":"10.21125/inted.2022.1580","title":"SOME FEATURES OF THE NATIONAL LANGUAGE AS A FOREIGN LANGUAGE PROFICIENCY ASSESSMENT SYSTEMS","year":2022,"lang":"en","type":"article","venue":"INTED proceedings","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Linguistics; Artificial intelligence; Foreign 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004851814,0.0001098432,0.0001326129,0.0001183449,0.0005569356,0.0001469344,0.0003385456,0.00002245711,0.001237641],"category_scores_gemma":[0.0001459932,0.0000761017,0.00008618805,0.00008222782,0.00008300361,0.0001517868,0.0001463541,0.0004936073,0.000006892271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009991634,"about_ca_system_score_gemma":0.0000659852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001436082,"about_ca_topic_score_gemma":0.00001565808,"domain_scores_codex":[0.9988646,0.000036352,0.0001921126,0.0001749195,0.0005560748,0.0001759652],"domain_scores_gemma":[0.9995422,0.00004812502,0.0001937825,0.00006626656,0.0001250383,0.00002455887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001371688,0.00007933862,0.0003818889,0.000091977,0.00004722827,0.000003810403,0.219935,0.00003102162,0.005613557,0.7664818,0.006691433,0.0006292455],"study_design_scores_gemma":[0.0004879502,0.0002660053,0.0008144464,0.0001201316,0.00003998257,0.0001015074,0.9564472,0.000922329,0.002024888,0.001271867,0.03721793,0.0002857246],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.758157,0.0007364497,7.446194e-7,0.0002175253,0.0003363922,0.0002206154,0.00003683304,0.00008807261,0.2402064],"genre_scores_gemma":[0.9754736,5.758171e-7,0.00001452743,0.0006028248,0.0004868406,0.000100964,0.00001300161,0.00001874379,0.0232889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7652099,"threshold_uncertainty_score":0.9996753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581680778601954,"score_gpt":0.2692618602694976,"score_spread":0.253445052483478,"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."}}