{"id":"W4380682783","doi":"10.1002/rrq.511","title":"Is a <scp>Phone‐Based</scp> Language and Literacy Assessment a Reliable and Valid Measure of Children's Reading Skills in <scp>Low‐Resource</scp> Settings?","year":2023,"lang":"en","type":"article","venue":"Reading Research Quarterly","topic":"Child Development and Digital Technology","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Jacobs Foundation","keywords":"Pseudoword; Phone; Vocabulary; Literacy; Phonological awareness; Psychology; Resource (disambiguation); Phonemic awareness; Reading (process); Reading comprehension; Comprehension; Applied psychology; Computer science; 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":[0.004967805,0.0002403344,0.0004443885,0.001324349,0.0005390322,0.0005223835,0.0004391789,0.0002908491,0.000009124606],"category_scores_gemma":[0.002357841,0.0002421706,0.00007520556,0.002486447,0.0005388389,0.0005369266,0.0001625524,0.0006885524,0.0000410937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001655102,"about_ca_system_score_gemma":0.0003559218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001015718,"about_ca_topic_score_gemma":0.0001494196,"domain_scores_codex":[0.996017,0.0003371914,0.000476925,0.000698806,0.001265605,0.001204423],"domain_scores_gemma":[0.9962196,0.002743908,0.000156444,0.0003741734,0.0002127606,0.0002931496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001411593,0.0003765457,0.4786177,0.0004465794,0.0001401794,0.0002666224,0.3633033,0.000004899559,0.006860622,0.007587611,0.05882035,0.08356147],"study_design_scores_gemma":[0.006226698,0.002184564,0.5499816,0.005960045,0.00006774029,0.00006060923,0.3283812,0.001530745,0.0165083,0.01967308,0.06872956,0.0006958097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9797199,0.0002934001,0.00002248169,0.001001786,0.00004710353,0.0006412152,0.00003176974,0.0002398178,0.01800246],"genre_scores_gemma":[0.9950369,0.0001394454,0.0007154559,0.00009349098,0.00008973626,0.00005598474,0.00004294025,0.00003889887,0.003787176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08286566,"threshold_uncertainty_score":0.9875429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02177586229239166,"score_gpt":0.3597768400884219,"score_spread":0.3380009777960302,"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."}}