{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004203166,0.0009838167,0.0005776754,0.001439695,0.002470203,0.007795618,0.001417125,0.002859615,0.02168527],"category_scores_gemma":[0.01866777,0.0004013823,0.00053077,0.001472851,0.006084315,0.01375533,0.002332668,0.007440304,0.01269883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003559528,"about_ca_system_score_gemma":0.005282644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01905216,"about_ca_topic_score_gemma":0.02361348,"domain_scores_codex":[0.9966328,0.001681187,0.0001172544,0.0003183202,0.0009887263,0.0002617601],"domain_scores_gemma":[0.9938146,0.002737351,0.0002230749,0.0004706371,0.00212867,0.0006256899],"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":[0.00002150357,0.00007875609,0.001239767,0.0002109506,0.000009405158,0.000125763,0.007372425,0.0005238327,0.0005199052,0.2367142,0.4255759,0.3276076],"study_design_scores_gemma":[0.00001104341,0.00008541594,0.002305955,0.001066353,0.0000147404,0.000490182,0.01191203,0.001386622,0.001491902,0.1850198,0.7961446,0.00007133483],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.004837934,0.007525376,0.05534619,0.1108797,0.005630924,0.0001053388,0.0002246702,0.001502189,0.8139477],"genre_scores_gemma":[0.1788314,0.008507995,0.06298126,0.04160894,0.002511688,0.0003359513,0.0005376792,0.002422264,0.7022629],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02168527,"threshold_uncertainty_score":0.07254446,"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."}}