{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02351309,0.0005945485,0.001222602,0.002806938,0.0009536344,0.003000185,0.0008306199,0.00168976,0.001441852],"category_scores_gemma":[0.207779,0.0004595227,0.0009461255,0.001660696,0.001930781,0.004224015,0.002230418,0.00144643,0.0008268132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007694546,"about_ca_system_score_gemma":0.001366214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008888372,"about_ca_topic_score_gemma":0.007461268,"domain_scores_codex":[0.9786832,0.01321704,0.001201255,0.002790313,0.003440287,0.0006678543],"domain_scores_gemma":[0.6647978,0.2838154,0.02301879,0.01366452,0.01021086,0.004492573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003475696,0.00009059297,0.9670004,0.00004290809,0.000221606,0.00007930891,0.001597592,0.002753749,0.0003122801,0.0004561726,0.0006786022,0.0264191],"study_design_scores_gemma":[0.00006270234,0.0005587064,0.8976543,0.0001322838,0.0001456153,0.0003881294,0.002919479,0.08058336,0.001646335,0.01297619,0.00275561,0.0001772847],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827922,0.0006694256,0.01185702,0.0006911031,0.00009733877,0.00003942899,0.0002104955,0.0001025574,0.003540355],"genre_scores_gemma":[0.9976493,0.00005476653,0.001859477,0.00006970493,0.00004750446,0.00001469701,0.00009991791,0.00001589732,0.000188818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02351309,"threshold_uncertainty_score":0.1243506,"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."}}