{"id":"W7108456678","doi":"10.1080/10409289.2025.2581998","title":"Effect Size Thresholds in Early Literacy: Defining Benchmarks for Phonemic Awareness Research","year":2025,"lang":"en","type":"article","venue":"Early Education and Development","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Phonemic awareness; Phonological awareness; Phonology; Cognition; Context effect; Statistical analysis; Perception","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":[0.00202644,0.0001377828,0.0001983739,0.0005049425,0.0002719518,0.0001266947,0.0002124386,0.0001811906,0.0002832927],"category_scores_gemma":[0.0002595817,0.0001337114,0.00002404787,0.0005240506,0.00009214896,0.00006911251,0.0001046038,0.0003932607,0.00009113477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221343,"about_ca_system_score_gemma":0.001227716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008210909,"about_ca_topic_score_gemma":0.0001038749,"domain_scores_codex":[0.9982758,0.0002992373,0.0003050139,0.0004450042,0.0001742601,0.0005006942],"domain_scores_gemma":[0.9978864,0.001520656,0.00003673747,0.0002554511,0.0002028025,0.00009791847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003701954,0.000340974,0.719565,0.0001035505,0.00005247756,0.000002479632,0.05365821,4.347782e-7,0.0003063073,0.002675247,0.009691548,0.2132335],"study_design_scores_gemma":[0.0009807389,0.0001849072,0.975186,0.0001295974,0.000003190486,0.000002991914,0.0005307776,0.000004879835,0.001014491,0.001863471,0.01996223,0.0001366906],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987104,0.001790874,0.00007170019,0.0005355987,0.001214358,0.0006581927,0.000003526953,0.00001591969,0.008605824],"genre_scores_gemma":[0.9898989,0.00003136455,0.001178132,0.0001786387,0.00004380657,0.001185978,0.00004412041,0.00001299571,0.007426062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.255621,"threshold_uncertainty_score":0.5452592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03436409683491862,"score_gpt":0.4501142950077062,"score_spread":0.4157501981727876,"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."}}