{"id":"W2312774039","doi":"10.18192/olbiwp.v4i0.1106","title":"Multidimensionality of assessment in the Common European Framework of Reference for languages (CEFR)","year":2012,"lang":"en","type":"article","venue":"OLBI Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perspective (graphical); Context (archaeology); Process (computing); Raising (metalworking); Domain (mathematical analysis); Computer science; Psychology; Linguistics; Artificial intelligence; Geography; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004231771,0.00005369159,0.000131852,0.00003573719,0.0001692188,0.00002342895,0.0003010517,0.00003672477,0.0001111686],"category_scores_gemma":[0.0001687776,0.00003542975,0.00005994505,0.000114031,0.00009910847,0.0001270393,0.00003321366,0.0002444516,0.00000184362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003568338,"about_ca_system_score_gemma":0.00005636633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001532701,"about_ca_topic_score_gemma":0.0001152172,"domain_scores_codex":[0.998485,0.0005977387,0.0002585103,0.00005017343,0.0004151331,0.0001933924],"domain_scores_gemma":[0.9989441,0.0005893611,0.0002357232,0.00009696752,0.00008734377,0.00004651612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000321842,0.0004694205,0.8704771,0.0000181434,0.00003377978,0.000002665063,0.03210212,0.000009093084,0.0007604516,0.08798231,0.002288583,0.005824191],"study_design_scores_gemma":[0.0003013545,0.00005622867,0.9613544,0.00007739876,0.00001948229,0.000001918523,0.02711408,0.000007633872,0.00005623266,0.001222006,0.009725062,0.00006422424],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9456624,0.0003219505,0.0006517015,0.001271916,0.0002548222,0.0001798421,0.000009715556,0.000004657857,0.05164295],"genre_scores_gemma":[0.9930778,0.0001006202,0.006346906,0.00007403086,0.0003026217,0.000002100029,0.000002051568,0.000004153727,0.00008969728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09087733,"threshold_uncertainty_score":0.1466656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07346238474137637,"score_gpt":0.4446475901687345,"score_spread":0.3711852054273581,"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."}}