{"id":"W2800630406","doi":"10.1111/1467-9817.12241","title":"What methods of scoring young children's spelling best predict later spelling performance?","year":2018,"lang":"en","type":"article","venue":"Journal of Research in Reading","topic":"Reading and Literacy Development","field":"Psychology","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Sciences and Humanities Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Spelling; Psychology; Correctness; Linguistics; Test (biology); Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01381655,0.0001743249,0.000465061,0.001670754,0.0001436993,0.0002065429,0.0005386251,0.0001432887,0.0002989135],"category_scores_gemma":[0.0002259488,0.0001448122,0.0001192068,0.0008965136,0.0002505739,0.0009036787,0.0001147964,0.001240277,0.0001179461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002188906,"about_ca_system_score_gemma":0.0001228647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000770118,"about_ca_topic_score_gemma":0.000003923644,"domain_scores_codex":[0.9962562,0.0007073338,0.001114375,0.0002949572,0.0008417496,0.0007853618],"domain_scores_gemma":[0.9977789,0.0006869061,0.0004211872,0.0003281393,0.0005900653,0.0001948036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005757323,0.0002323651,0.8449045,0.0001691142,0.0003064418,0.0001979007,0.02585689,0.0002275949,0.007356434,0.0002367889,0.0003931924,0.119543],"study_design_scores_gemma":[0.008166118,0.007243852,0.5617409,0.03919286,0.0001947048,0.006394839,0.03287246,0.009687836,0.3134172,0.003692304,0.01559696,0.001799963],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845303,0.001154933,0.001520051,0.0001203872,0.002650063,0.0001790049,7.749161e-7,0.000008590653,0.009835926],"genre_scores_gemma":[0.9617291,0.00161008,0.03303181,0.00001120249,0.001399727,0.000002584389,0.0000011523,0.00003591753,0.002178419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3060608,"threshold_uncertainty_score":0.5905272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1160578144778716,"score_gpt":0.4825821632774959,"score_spread":0.3665243487996243,"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."}}