{"id":"W4409148165","doi":"10.3758/s13428-025-02656-9","title":"VOC-ADO: A lexical database for French-speaking adolescents","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation","funders":"Agence Nationale de la Recherche","keywords":"Vocabulary; Computer science; Lemma (botany); Psychology; Linguistics; Lexical database; Mathematics education; Natural language processing","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":[0.0009935801,0.001101104,0.001128348,0.007239059,0.000735061,0.00198756,0.000883523,0.0008511507,0.02847165],"category_scores_gemma":[0.006494912,0.0003789891,0.0005291555,0.003637075,0.0002521233,0.001952676,0.001359495,0.00045729,0.01322404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006829574,"about_ca_system_score_gemma":0.002048468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01222934,"about_ca_topic_score_gemma":0.01215596,"domain_scores_codex":[0.9991584,0.0001991974,0.0002085736,0.0002263634,0.0001435301,0.00006392124],"domain_scores_gemma":[0.9966245,0.001523805,0.0002590696,0.0003426445,0.001019309,0.0002306294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002696033,0.0005379518,0.03207136,0.006813822,0.0003555638,0.002007383,0.004333157,0.001725789,0.03435161,0.009163401,0.3425388,0.5634052],"study_design_scores_gemma":[0.0005558665,0.0003832769,0.0629385,0.001069939,0.0005068455,0.002211723,0.003432196,0.008895769,0.01263349,0.006065245,0.9010292,0.000277938],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.09861523,0.00274454,0.05152531,0.0003241394,0.0002440287,0.001215155,0.8002009,0.02052965,0.02460116],"genre_scores_gemma":[0.1548719,0.001339052,0.08095579,0.0002094453,0.0001014711,0.002411972,0.748798,0.003250919,0.008061498],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02847165,"threshold_uncertainty_score":0.09524715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3489859521934305,"score_gpt":0.6063080813811523,"score_spread":0.2573221291877218,"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."}}