{"id":"W4395077771","doi":"10.1177/01427237241245500","title":"Evaluating English-language morphological awareness assessments","year":2024,"lang":"en","type":"article","venue":"First Language","topic":"Reading and Literacy Development","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Reading comprehension; Reading (process); Comprehension; Set (abstract data type); Psychology; Linguistics; Computer science; Cognitive psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"category_scores_codex":[0.0006983622,0.0002269038,0.0002278959,0.0001509311,0.0001298678,0.0001948007,0.0002808216,0.0001519811,0.009509648],"category_scores_gemma":[0.0001528794,0.0001820687,0.0001039573,0.0003160178,0.00003866158,0.0001176492,0.00009723783,0.0003363081,0.00172425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025556,"about_ca_system_score_gemma":0.00005554257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002712914,"about_ca_topic_score_gemma":0.00001404941,"domain_scores_codex":[0.9981481,0.0001575738,0.0003203342,0.0005907204,0.0003244834,0.0004587591],"domain_scores_gemma":[0.9990318,0.0003242957,0.00004841863,0.0004483095,0.00003791981,0.000109201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001352517,0.0005155482,0.01827048,0.0004173107,0.0005935981,0.01405348,0.6523033,0.00007536698,0.005381245,0.004657183,0.0456996,0.2578976],"study_design_scores_gemma":[0.00628803,0.001895586,0.1844233,0.002954778,0.0005591123,0.001729424,0.158203,0.0125017,0.005327451,0.0005300732,0.6208221,0.00476556],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399161,0.003126388,0.0005034713,0.0001060634,0.003358279,0.000211303,0.00004741759,0.0006483718,0.05208262],"genre_scores_gemma":[0.9745954,0.000005260055,0.001825427,0.0002238473,0.0007072529,0.0001439257,0.0001662272,0.00004511576,0.02228758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5751225,"threshold_uncertainty_score":0.999053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05795613321988979,"score_gpt":0.4397926648852263,"score_spread":0.3818365316653365,"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."}}