{"id":"W4408745144","doi":"10.23977/aetp.2025.090120","title":"A Study of Second Language Vocabulary Acquisition Based on Corpus Linguistics","year":2025,"lang":"en","type":"article","venue":"Advances in Educational Technology and Psychology","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Linguistics; Corpus linguistics; Vocabulary; Applied linguistics; Computer science; Second-language acquisition; Natural language processing; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002031307,0.0001281524,0.0002180259,0.001218338,0.00006495704,0.000003927388,0.0001774334,0.0002286696,0.004872567],"category_scores_gemma":[0.0002376127,0.0001341924,0.00002200976,0.0007589462,0.0002119847,0.00002695954,0.0000218046,0.0003587374,0.00002391556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001961545,"about_ca_system_score_gemma":0.00003705412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007189824,"about_ca_topic_score_gemma":0.00003793154,"domain_scores_codex":[0.9989092,0.0001446615,0.000309025,0.0003903248,0.00006257668,0.0001841985],"domain_scores_gemma":[0.9989977,0.000401179,0.0001275459,0.0003815448,0.00006980205,0.00002221914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0009936262,0.006866768,0.2825776,0.00008996684,0.0001307069,0.000171018,0.007459847,0.0001797605,0.0005545717,0.6317739,0.00279019,0.06641207],"study_design_scores_gemma":[0.007374847,0.002316462,0.8368261,0.000165321,0.00005703354,0.00008123702,0.03165502,0.00006031792,0.0002129708,0.07156391,0.04923303,0.0004537453],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9048719,0.01519483,0.0002651151,0.001371927,0.001786818,0.0002803229,0.00001028126,0.00005428426,0.07616451],"genre_scores_gemma":[0.9917519,0.00002263224,0.0004255976,0.006715711,0.00008034124,0.0001199123,0.00002771151,0.000008965291,0.0008472453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.56021,"threshold_uncertainty_score":0.9960371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009847614990049332,"score_gpt":0.3778815165353407,"score_spread":0.3680339015452914,"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."}}