{"id":"W4291825485","doi":"10.1177/02655322221114895","title":"Book Review: <i>Multilingual Testing and Assessment</i>","year":2022,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Linguistics; Language assessment; Mathematics education; Philosophy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001220556,0.00009499902,0.0001381737,0.00005121867,0.001291258,0.0000563676,0.0001815789,0.00002129179,0.00180676],"category_scores_gemma":[0.007004704,0.0001043693,0.00002445233,0.0004953578,0.00008317587,0.0001016645,0.00013468,0.0003206505,0.00000910903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009118509,"about_ca_system_score_gemma":0.0004635283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005841106,"about_ca_topic_score_gemma":0.00007474955,"domain_scores_codex":[0.9986327,0.0003118299,0.0002101324,0.0002199265,0.0003207093,0.0003047446],"domain_scores_gemma":[0.9982999,0.00120373,0.0001398741,0.0001454923,0.00007968374,0.0001313434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003277423,0.0001472218,0.02339695,0.000386411,0.00001575069,0.00007779303,0.100123,0.00002965985,0.001928912,0.0006457123,0.0976748,0.7755705],"study_design_scores_gemma":[0.0002011089,0.0000373905,0.001846235,0.0001890654,0.00002322997,0.00002480707,0.01496739,0.0006439475,0.00003107251,0.00003702471,0.9817635,0.0002352394],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1619024,0.2677948,0.00001012985,0.006588053,0.0007303461,0.000966389,0.0000318881,0.0008230794,0.5611529],"genre_scores_gemma":[0.5140581,0.003218228,0.0752665,0.311352,0.004009844,0.0004363199,0.00006076443,0.0001465412,0.09145164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8840887,"threshold_uncertainty_score":0.9991058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0868325680279467,"score_gpt":0.4760949100818659,"score_spread":0.3892623420539192,"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."}}