{"id":"W2086143772","doi":"10.1075/ml.9.1.02wil","title":"Estimating second language productive vocabulary size","year":2014,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Vocabulary; Animacy; Cognitive psychology; Stimulus (psychology); Psychology; Lexical access; Computer science; Natural language processing; Linguistics; Artificial intelligence; Cognition","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":[0.0004915853,0.0001197354,0.0001207029,0.00002707734,0.0001806142,0.00003450872,0.0001791669,0.00004597442,0.0780393],"category_scores_gemma":[0.00009753986,0.00008636533,0.00005247489,0.00007909244,0.00007968485,0.00006837419,0.00004824976,0.0002311759,0.001317603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002714562,"about_ca_system_score_gemma":0.000006793386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005450139,"about_ca_topic_score_gemma":0.000005765333,"domain_scores_codex":[0.9989884,0.0002764059,0.0001469485,0.0002468016,0.0001097286,0.0002316512],"domain_scores_gemma":[0.9992957,0.0001942716,0.00008666608,0.0003668328,0.00001144821,0.0000450924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004609117,0.000483405,0.001008681,0.0000914298,0.000464619,0.0001460205,0.4798394,0.0001023874,0.1642582,0.02448184,0.04066354,0.2879996],"study_design_scores_gemma":[0.01630664,0.002835776,0.189442,0.0004223328,0.0003953077,0.002966242,0.3886735,0.01184997,0.1428934,0.008529781,0.2317284,0.003956662],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.895922,0.0008031031,0.0001771661,0.0007137259,0.0009356501,0.000213672,0.000006060564,0.0001158549,0.1011128],"genre_scores_gemma":[0.9756429,9.558399e-8,0.0006472144,0.007632893,0.0007552308,0.00002678369,0.000021205,0.00002357998,0.01525008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2840429,"threshold_uncertainty_score":0.99946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009818832915785381,"score_gpt":0.2948278677782564,"score_spread":0.285009034862471,"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."}}