{"id":"W4327916713","doi":"10.1101/2023.03.20.23287486","title":"Characteristics of dynamic assessments of word reading skills and their implications for validity: A systematic review and meta-analysis","year":2023,"lang":"en","type":"review","venue":"medRxiv","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Reading (process); Psychology; Word (group theory); Test (biology); Meta-analysis; Natural language processing; Cognitive psychology; Computer science; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03262347,0.002197999,0.01413262,0.009247196,0.0007231606,0.004345983,0.002558711,0.00188997,0.003697252],"category_scores_gemma":[0.1036625,0.001317795,0.02004247,0.009226445,0.001218536,0.002865572,0.001907827,0.001568128,0.0003224045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0032583,"about_ca_system_score_gemma":0.006530167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004696711,"about_ca_topic_score_gemma":0.01253562,"domain_scores_codex":[0.981558,0.006390193,0.007720772,0.001487892,0.002527226,0.0003159844],"domain_scores_gemma":[0.9069604,0.07599949,0.009787737,0.001750236,0.005152719,0.0003495074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.0005039852,0.00002126499,0.002457815,0.8415466,0.1225286,0.00006941093,0.0001276317,0.0002046529,0.0001556281,0.0002425824,0.0006423228,0.03149953],"study_design_scores_gemma":[0.0004330503,0.0002405603,0.007161618,0.3090144,0.6750585,0.000233023,0.0001599297,0.000178529,0.0003021308,0.0006993388,0.006473306,0.00004565844],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001175862,0.9974127,0.0004329679,0.0001297027,0.00007456239,0.0002930474,0.0002885803,0.00001098007,0.0001815943],"genre_scores_gemma":[0.0579194,0.9364497,0.002148784,0.0006234081,0.0001539877,0.00181528,0.0006944,0.00002486446,0.0001701691],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03262347,"threshold_uncertainty_score":0.1725315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2910477597929519,"score_gpt":0.5132938112503193,"score_spread":0.2222460514573673,"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."}}