{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006276626,0.0008333455,0.0006961958,0.002116185,0.0002756063,0.001597834,0.0007445109,0.0009148704,0.001253166],"category_scores_gemma":[0.02595336,0.0002719502,0.0006360054,0.001753583,0.0007410213,0.00176424,0.0004724631,0.0007631904,0.0007363742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004949876,"about_ca_system_score_gemma":0.001172944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005852806,"about_ca_topic_score_gemma":0.01672357,"domain_scores_codex":[0.9981164,0.0008057297,0.0002366256,0.0003752892,0.000356403,0.0001096319],"domain_scores_gemma":[0.9745598,0.01104895,0.008166493,0.001129635,0.0035584,0.001536709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000955281,0.00006501225,0.975276,0.00009207749,0.00009151083,0.0000196374,0.0001438653,0.0001766739,0.0004587921,0.000050493,0.0003391691,0.02319141],"study_design_scores_gemma":[0.00001386185,0.0004203564,0.9955118,0.000124734,0.00007028737,0.0001506033,0.0003231212,0.001749611,0.0009992407,0.0002777974,0.0003332107,0.00002524948],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9816085,0.00421164,0.009518012,0.0005690116,0.00009986175,0.00009407051,0.0009755376,0.0001858852,0.002737499],"genre_scores_gemma":[0.9806464,0.001165825,0.01688238,0.00005242712,0.00004295622,0.0000777709,0.0005767116,0.00002414677,0.0005314568],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006276626,"threshold_uncertainty_score":0.03319436,"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."}}