{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04922393,0.0004996574,0.0005139352,0.002359252,0.0005665605,0.002038297,0.0007004577,0.0007746584,0.0009193001],"category_scores_gemma":[0.1266352,0.0003418778,0.0009727496,0.001156365,0.001706484,0.001848604,0.003654448,0.0007623974,0.000271189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006286842,"about_ca_system_score_gemma":0.0006914506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001308608,"about_ca_topic_score_gemma":0.002516886,"domain_scores_codex":[0.9681037,0.01937824,0.002110931,0.003604987,0.006220652,0.0005814502],"domain_scores_gemma":[0.8593172,0.1038139,0.01161025,0.01145614,0.01273185,0.001070573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000521718,0.0002715379,0.9383464,0.00008064509,0.0004402846,0.00005709891,0.004310286,0.001142688,0.002505312,0.00054202,0.0001286994,0.05165318],"study_design_scores_gemma":[0.0000492138,0.001577709,0.9746184,0.00007102369,0.0002728486,0.0003153568,0.002158748,0.01407197,0.004425126,0.001633821,0.0007606396,0.00004516495],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832049,0.0001433459,0.01354999,0.00006122079,0.00001534769,0.0001729258,0.00006159941,0.00004469272,0.002745894],"genre_scores_gemma":[0.9954163,0.00002919574,0.004059135,0.00002254476,0.00001032655,0.000169752,0.00008431254,0.00001394847,0.0001945344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04922393,"threshold_uncertainty_score":0.2603241,"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."}}