{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003949882,0.0003916628,0.0002585602,0.002647166,0.001534057,0.00282002,0.0009353074,0.0004257269,0.004189135],"category_scores_gemma":[0.01305696,0.0002734877,0.0003244476,0.001457384,0.001445471,0.002004962,0.002691252,0.0008919235,0.0005636555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001553191,"about_ca_system_score_gemma":0.004033334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003832932,"about_ca_topic_score_gemma":0.01168752,"domain_scores_codex":[0.9977263,0.001398565,0.0001427994,0.0002567954,0.000411501,0.00006400188],"domain_scores_gemma":[0.9926009,0.004892351,0.0004168037,0.0006559711,0.001166035,0.0002680548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003224074,0.00144092,0.01018646,0.00361565,0.00009239082,0.001095837,0.1579027,0.004849306,0.07816198,0.03896929,0.006999241,0.6963639],"study_design_scores_gemma":[0.0003144513,0.002672817,0.03614915,0.004351608,0.0004084138,0.002028071,0.1715172,0.03096612,0.1165033,0.0346927,0.6000748,0.000321303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5328107,0.001406926,0.3551299,0.001755738,0.0003356178,0.0116269,0.002018152,0.001730103,0.09318589],"genre_scores_gemma":[0.3634484,0.001005647,0.6179546,0.000250573,0.00003914787,0.005608831,0.001054123,0.0003424015,0.01029616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004189135,"threshold_uncertainty_score":0.02088922,"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."}}