{"id":"W4389294437","doi":"10.1080/15434303.2023.2288253","title":"Validity Arguments for Automated Essay Scoring of Young Students’ Writing Traits","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Writing assessment; Consistency (knowledge bases); Context (archaeology); Vocabulary; Psychology; Inference; Argument (complex analysis); Formative assessment; Trait; Artificial intelligence; Natural language processing; Computer science; Mathematics education; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.001113247,0.0001393121,0.0002202543,0.0001334027,0.0001303798,0.0002162125,0.0007928991,0.00005846357,0.000006747511],"category_scores_gemma":[0.00002646708,0.0001383288,0.0000959745,0.0004695973,0.00002138302,0.0005182773,0.00006507311,0.0000880709,0.00001430536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009068496,"about_ca_system_score_gemma":0.00007510196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006737553,"about_ca_topic_score_gemma":0.00003418868,"domain_scores_codex":[0.9982348,0.0001219398,0.0004217942,0.0003978873,0.0004916967,0.0003318607],"domain_scores_gemma":[0.9989762,0.0002295976,0.0001845904,0.0004533818,0.0000901913,0.00006602624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003311682,0.00147708,0.153676,0.001031753,0.0002530589,0.00007972993,0.09369092,0.0002957399,0.1997186,0.03360007,0.001006978,0.5151369],"study_design_scores_gemma":[0.001115786,0.0006074037,0.8524105,0.0001003498,0.00002777803,0.000006214538,0.005072051,0.1351477,0.003642167,0.00149702,0.00004980215,0.0003232574],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7880567,0.0000082329,0.2101454,0.0001180656,0.0002157385,0.0004129795,0.00001994741,0.0008196266,0.0002032719],"genre_scores_gemma":[0.9802725,9.708205e-7,0.01933962,0.00002606102,0.00005208327,0.0001117667,0.00004693149,0.00001196375,0.0001381106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6987345,"threshold_uncertainty_score":0.5640885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0296680655231284,"score_gpt":0.359881211422216,"score_spread":0.3302131458990876,"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."}}