{"id":"W4412969591","doi":"10.1177/02655322251348956","title":"Investigating construct representativeness and linguistic equity of automated oral reading fluency assessment with prosody","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies","funders":"Iran Science Elites Federation; University of Toronto","keywords":"Prosody; Fluency; Psychology; Ell; Natural language processing; Linguistics; Reading comprehension; Reading (process); Cognitive psychology; Computer science; Artificial intelligence; Mathematics education; Speech recognition; Teaching method; Vocabulary development","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":[],"consensus_categories":[],"category_scores_codex":[0.0005905341,0.0001595972,0.0002892983,0.0001309257,0.0001339846,0.00005739102,0.0001224568,0.00005154975,0.00002796008],"category_scores_gemma":[0.001464815,0.0001345098,0.00001576145,0.0005225188,0.0001723755,0.00005518448,0.0001334808,0.0001881072,0.000001514176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006048804,"about_ca_system_score_gemma":0.0001546884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001128564,"about_ca_topic_score_gemma":0.00001027027,"domain_scores_codex":[0.9986468,0.0001679299,0.0003940305,0.0003623433,0.0001525348,0.000276393],"domain_scores_gemma":[0.998535,0.0007705357,0.0002423141,0.0002467401,0.000143951,0.00006141149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001490088,0.00004736005,0.916972,0.0003527353,0.0001207863,0.0001221841,0.02369158,0.000028536,0.0189666,0.006431818,0.00004191571,0.03320953],"study_design_scores_gemma":[0.001836812,0.0001943628,0.9677733,0.003299157,0.0001291546,0.0001636559,0.0102658,0.008894078,0.00549959,0.001460838,0.00003580002,0.0004474245],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9338176,0.0001451094,0.0005653152,0.00002280596,0.0001579204,0.0002457548,0.000006272701,0.0003478624,0.06469138],"genre_scores_gemma":[0.9152763,2.566853e-7,0.08413101,0.00006670257,0.00002402311,0.00003345989,0.00001211076,0.00001417085,0.0004419631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08356569,"threshold_uncertainty_score":0.5485149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03767559474110727,"score_gpt":0.4197115117810315,"score_spread":0.3820359170399242,"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."}}