{"id":"W2900390458","doi":"10.1177/0731948718803296","title":"The Potential for Automated Text Evaluation to Improve the Technical Adequacy of Written Expression Curriculum-Based Measurement","year":2018,"lang":"en","type":"article","venue":"Learning Disability Quarterly","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Curriculum-based measurement; Construct validity; Psychology; Curriculum; Writing assessment; Expression (computer science); Construct (python library); Rating scale; Scale (ratio); Quality (philosophy); Natural language processing; Artificial intelligence; Machine learning; Computer science; Mathematics education; Clinical psychology; Psychometrics; Developmental psychology; Pedagogy; Curriculum development","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.009754949,0.0000996038,0.0001229823,0.00002090877,0.002009888,0.0001584299,0.0003258306,0.0000905987,0.00003265778],"category_scores_gemma":[0.004417988,0.0000643535,0.0001067172,0.0002296189,0.0006379744,0.0001042069,0.0000149479,0.0001634615,0.0000149854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002593557,"about_ca_system_score_gemma":0.0002698354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008362464,"about_ca_topic_score_gemma":0.001109742,"domain_scores_codex":[0.9969749,0.001096637,0.0003542274,0.0002910784,0.0009385837,0.0003444989],"domain_scores_gemma":[0.9978591,0.0005421744,0.000192559,0.0003210918,0.001008495,0.00007664607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004213862,0.001388598,0.01423055,0.0001459884,0.00004552152,9.034934e-8,0.05062014,0.0008463903,0.102131,0.003164175,0.007480509,0.8195257],"study_design_scores_gemma":[0.004665724,0.01034309,0.3194733,0.001184512,0.0005508856,0.00000162453,0.3442138,0.2594487,0.008153003,0.01057071,0.03996076,0.00143387],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978217,0.00003879286,0.005373599,0.01298181,0.0005508945,0.001814841,0.000004128699,0.0003285941,0.0006903497],"genre_scores_gemma":[0.9982166,3.802225e-7,0.0007254481,0.00004394752,0.0006104216,0.0003448626,0.000006932737,0.0000104747,0.00004087637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8180918,"threshold_uncertainty_score":0.9992893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245414221554363,"score_gpt":0.3552407992022679,"score_spread":0.3306993770468316,"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."}}