{"id":"W4245172457","doi":"10.35542/osf.io/ytvn4","title":"Is a Phone-Based Language and Literacy Assessment a Reliable and Valid Measure of Children’s Reading Skills in Low-Resource Settings?","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Child Development and Digital Technology","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pseudoword; Phone; Literacy; Vocabulary; Resource (disambiguation); Phonological awareness; Reading (process); Psychology; Phonemic awareness; Computer science; Applied psychology; Pedagogy; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008086598,0.0002138216,0.0004507055,0.0002722607,0.0001066963,0.0003006141,0.0002213945,0.0003723211,0.0001064767],"category_scores_gemma":[0.0002510603,0.00021172,0.00006828358,0.0003176776,0.0001812251,0.0001461084,0.000519913,0.0004210264,9.497849e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009526635,"about_ca_system_score_gemma":0.0004359848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002327582,"about_ca_topic_score_gemma":0.0005270042,"domain_scores_codex":[0.9982807,0.00008132575,0.0003844663,0.0005644349,0.0003866551,0.0003024256],"domain_scores_gemma":[0.9991952,0.0001437153,0.0002073321,0.0002782287,0.00008791819,0.00008766436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003374469,0.0005938119,0.8027158,0.0006071561,0.0001711572,0.00007982006,0.1390944,0.00003001909,0.000505382,0.0033978,0.002585177,0.05018571],"study_design_scores_gemma":[0.01182814,0.0002810327,0.7335929,0.02642271,0.0003537849,0.0000503911,0.1353484,0.001462019,0.0612404,0.007720807,0.01548536,0.006214108],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9684604,0.0006802921,0.00009541973,0.001846756,0.00005621148,0.0004211873,0.00001920862,0.00009563304,0.02832489],"genre_scores_gemma":[0.9927658,0.000144196,0.005262154,0.0005580038,0.00003200274,0.00002149238,0.00006449984,0.00001577817,0.001136095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06912295,"threshold_uncertainty_score":0.863369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009107779147927049,"score_gpt":0.2990495783766641,"score_spread":0.289941799228737,"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."}}