{"id":"W4391927924","doi":"10.1080/15434303.2024.2311724","title":"The Development and Initial Validation of O-WSVLT, a Meaning-Recall Online L2 Spanish Vocabulary Levels Test","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Meaning (existential); Vocabulary; Linguistics; Test (biology); Language proficiency; Recall; Vocabulary development; Cognitive psychology; Mathematics education","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":[],"category_scores_codex":[0.0005859068,0.0001832388,0.0001926645,0.0001142033,0.0001516738,0.0001901663,0.0001693395,0.0000960251,0.004454937],"category_scores_gemma":[0.0000334276,0.0001400422,0.00006041227,0.0001817123,0.00006484816,0.0001436255,0.0000262795,0.0003095969,0.00007111816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004589388,"about_ca_system_score_gemma":0.00009852782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008839235,"about_ca_topic_score_gemma":0.00009513569,"domain_scores_codex":[0.9984726,0.0002013338,0.0004479366,0.0003368974,0.0002600162,0.0002812023],"domain_scores_gemma":[0.9988405,0.0006298001,0.0001155227,0.0002907131,0.00004946917,0.00007407299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0000452397,0.0003899719,0.001138133,0.0001586872,0.0004256057,0.0007384956,0.2016637,0.000002973693,0.01096854,0.009408382,0.001514887,0.7735454],"study_design_scores_gemma":[0.005472224,0.004472151,0.3194526,0.001172982,0.0005094934,0.0008546462,0.5836545,0.002372616,0.01213329,0.001243798,0.06651432,0.002147364],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802194,0.003948024,0.002686016,0.0003912582,0.0006382292,0.0002564985,0.00005378405,0.0001768407,0.01162991],"genre_scores_gemma":[0.9949679,0.000002268969,0.002162643,0.0005738481,0.0002987536,0.00003676175,0.0001724728,0.00003400696,0.001751311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.771398,"threshold_uncertainty_score":0.9964551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02360608309281445,"score_gpt":0.3639875715569394,"score_spread":0.3403814884641249,"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."}}