{"id":"W4414941398","doi":"10.1080/09588221.2025.2569343","title":"A corpus-based approach to developing vocabulary curriculum materials for Indigenous youth: AI-generated versus human-created content","year":2025,"lang":"en","type":"article","venue":"Computer Assisted Language Learning","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Mitel (Canada)","funders":"Social Sciences and Humanities Research Council of Canada; Federation for the Humanities and Social Sciences","keywords":"Indigenous; Vocabulary; Curriculum; Vocabulary development; Content analysis; Content (measure theory); Teaching method","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000713986,0.000439898,0.0006235631,0.0006271096,0.0006242978,0.000314421,0.0004432405,0.0003063357,0.001082916],"category_scores_gemma":[0.000173592,0.0004404276,0.0001788758,0.000800616,0.00004993285,0.00007806582,0.000131966,0.0005057381,0.00009996412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000271661,"about_ca_system_score_gemma":0.0001495741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006158361,"about_ca_topic_score_gemma":0.00001725468,"domain_scores_codex":[0.996775,0.0006889171,0.0006485508,0.000866521,0.0002515114,0.0007695287],"domain_scores_gemma":[0.9984899,0.0002228671,0.0002566987,0.0004909522,0.0003775581,0.0001620043],"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":[0.007714979,0.00399267,0.01095368,0.001831952,0.007134162,0.001866038,0.3231967,0.03211461,0.2596742,0.007776595,0.01535526,0.3283892],"study_design_scores_gemma":[0.1388604,0.009862165,0.2672874,0.006252969,0.003780305,0.0004977147,0.337835,0.04246608,0.09983446,0.00003780048,0.078228,0.01505774],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7280828,0.001434015,0.2651415,0.00009091507,0.001657971,0.001020839,0.00003234088,0.0006433289,0.001896291],"genre_scores_gemma":[0.9726648,5.666463e-7,0.01307032,0.009382524,0.0005140624,0.0003193252,0.002279119,0.00009294076,0.001676341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3133314,"threshold_uncertainty_score":0.9998302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05270630895946508,"score_gpt":0.3390531298623994,"score_spread":0.2863468209029343,"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."}}