{"id":"W4213141158","doi":"10.7820/vli.v10.2.mclean","title":"The internal consistency and accuracy of automatically scored written receptive meaning-recall data: A preliminary study","year":2021,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Japan Society for the Promotion of Science","keywords":"Recall; Consistency (knowledge bases); Meaning (existential); Internal consistency; Computer science; Natural language processing; Precision and recall; Psychology; Artificial intelligence; Cognitive psychology; Psychometrics; Developmental psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000632089,0.0001314367,0.0002108427,0.00007072484,0.0003833375,0.00009378902,0.0001328324,0.00008259261,0.0010579],"category_scores_gemma":[0.0009500567,0.0001057802,0.00003005399,0.0001581338,0.0001992734,0.0002037305,0.0002204279,0.0004776883,0.00001170972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001169144,"about_ca_system_score_gemma":0.0000395366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005042,"about_ca_topic_score_gemma":0.0000141405,"domain_scores_codex":[0.9981581,0.0007353608,0.0003632853,0.000409921,0.0001578385,0.000175473],"domain_scores_gemma":[0.9987273,0.0005162766,0.0002277882,0.0003457249,0.0001183769,0.00006455679],"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":[0.0008678806,0.0003087886,0.06632912,0.00007408481,0.0006611012,0.0002735298,0.04435189,0.0000180482,0.001345844,0.002624267,0.0006829581,0.8824625],"study_design_scores_gemma":[0.004774465,0.002733872,0.6276844,0.0003315575,0.0003211885,0.003191895,0.3395976,0.006302368,0.0001676714,0.000386334,0.01403095,0.000477656],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901214,0.00420799,0.000237869,0.0002136278,0.0004233824,0.0001717025,0.000003678419,0.00007089661,0.00454949],"genre_scores_gemma":[0.9979054,0.00009796832,0.0006289959,0.0001526015,0.0001180836,0.0000108491,0.00004589272,0.00001725889,0.001022968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8819848,"threshold_uncertainty_score":0.9998553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02340135669395839,"score_gpt":0.3193501383761505,"score_spread":0.2959487816821921,"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."}}