{"id":"W4380609605","doi":"10.1177/13621688231176067","title":"‘The wisdom of crowds’: When teacher judgments outperform word-frequency as a predictor of students’ vocabulary knowledge","year":2023,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Vocabulary; Psychology; Test (biology); Word lists by frequency; Word (group theory); Vocabulary development; Mathematics education; Linguistics; Teaching method; Natural language processing; Computer science","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":["insufficient_payload"],"category_scores_codex":[0.008144856,0.0001973305,0.0003261478,0.0005632043,0.0004790764,0.00008143458,0.001265388,0.0001859693,0.01468054],"category_scores_gemma":[0.001578318,0.0001513348,0.0001525202,0.0005886048,0.0003528597,0.0001169003,0.0004583605,0.001667364,0.001371984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009922191,"about_ca_system_score_gemma":0.0001009759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001591378,"about_ca_topic_score_gemma":0.00006855489,"domain_scores_codex":[0.9952635,0.001788989,0.0005676929,0.0004431873,0.001110551,0.0008261119],"domain_scores_gemma":[0.9972404,0.001236522,0.0001637847,0.001044642,0.0001495869,0.0001650865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005023272,0.001257856,0.1023313,0.0002638889,0.0007962459,0.0005451316,0.7220001,0.000005692239,0.01371427,0.005360576,0.04512288,0.1080998],"study_design_scores_gemma":[0.007041741,0.00163652,0.3583566,0.0008680745,0.0001176527,0.00009316935,0.5988104,0.0003350989,0.002066226,0.001849582,0.02796458,0.0008603666],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9292563,0.006852749,0.00001189355,0.0002238632,0.0003659624,0.0004661361,0.00001522047,0.0001655365,0.06264232],"genre_scores_gemma":[0.9277677,0.000016303,0.00009268798,0.0001213427,0.0003263449,0.00009931238,0.00004279096,0.00006180974,0.07147173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2560253,"threshold_uncertainty_score":0.9994056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05841451724138965,"score_gpt":0.4537021864922138,"score_spread":0.3952876692508241,"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."}}