{"id":"W4384788716","doi":"10.1007/978-3-031-33541-9_4","title":"Speaking “CEFR” about Local Tests: What Mapping a Placement Test to the CEFR Can and Can’t Do","year":2023,"lang":"en","type":"book-chapter","venue":"Educational linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Documentation; Test (biology); Computer science; Language proficiency; Language assessment; Local language; Psychology; Linguistics; Political science; Mathematics education; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005766251,0.0002742619,0.0002345598,0.0001468517,0.0008766268,0.000684062,0.0004266885,0.0001627962,0.0003924321],"category_scores_gemma":[0.003172345,0.0002486797,0.00006532094,0.000126574,0.0003074668,0.0000274436,0.0001928806,0.000339187,0.0002104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006804334,"about_ca_system_score_gemma":0.001672927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001265842,"about_ca_topic_score_gemma":0.01180307,"domain_scores_codex":[0.9979383,0.00002750141,0.0003467627,0.0004217265,0.0008855234,0.00038013],"domain_scores_gemma":[0.9972171,0.001458362,0.0002048142,0.0002425109,0.0006644458,0.000212743],"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":[0.00000510145,0.00005662216,0.003207251,0.00005052603,0.0001081447,0.000008984006,0.04352464,0.00004541438,7.693943e-7,0.8870397,0.06085268,0.005100127],"study_design_scores_gemma":[0.0000907974,0.00002702203,0.003627945,0.0006179331,0.00006711106,7.849092e-7,0.02199692,0.00001171484,2.265118e-7,0.01633368,0.956874,0.000351831],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001759629,0.001798227,0.00008372036,0.0326175,0.01492961,0.001227831,0.0003912018,0.0001132251,0.9486627],"genre_scores_gemma":[0.08588209,0.002523528,0.00132783,0.002504462,0.03632202,0.0001120173,0.0003358908,0.0001308665,0.8708613],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8960214,"threshold_uncertainty_score":0.9999965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0452173759265551,"score_gpt":0.3451583806976567,"score_spread":0.2999410047711016,"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."}}