{"id":"W4399368884","doi":"10.1044/2024_ajslp-23-00457","title":"Should We Stop Using Lexical Diversity Measures in Children's Language Sample Analysis?","year":2024,"lang":"en","type":"article","venue":"American Journal of Speech-Language Pathology","topic":"Language Development and Disorders","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"Mean length of utterance; Lexical diversity; Diversity (politics); Narrative; Psychology; Utterance; Lexical density; Sample (material); Vocabulary; Linguistics; Language development; Developmental psychology; Natural language processing; Computer science; Artificial intelligence; Lexical item; Sociology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001181893,0.0002967266,0.000813042,0.001514304,0.00009924418,0.00005360042,0.0004281797,0.0001506886,0.001569348],"category_scores_gemma":[0.0001960915,0.0002513634,0.00041343,0.001872546,0.0003918954,0.0001681668,0.0002190844,0.0007440789,0.00005029475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000139694,"about_ca_system_score_gemma":0.0001136442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0038231,"about_ca_topic_score_gemma":0.0005734848,"domain_scores_codex":[0.9973624,0.0005546799,0.0006295066,0.0004469538,0.0004337945,0.0005726471],"domain_scores_gemma":[0.9987716,0.0003231947,0.0003232259,0.000337497,0.00006718688,0.0001773078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003145448,0.0002780525,0.5831586,0.0000176688,0.001986808,0.02116979,0.1110073,0.0002245881,0.003415065,0.0003322048,0.0004021744,0.2776932],"study_design_scores_gemma":[0.004245548,0.001525852,0.693722,0.000247902,0.003716019,0.01181079,0.2793215,0.0005935321,0.001125624,0.0007053449,0.0009866284,0.001999306],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9801457,0.008928388,0.009260967,0.0004356456,0.0004847376,0.0001247096,0.00005108075,0.00006131698,0.0005074656],"genre_scores_gemma":[0.9928842,0.0001211494,0.005986407,0.0004678079,0.0003192612,0.000002162815,0.0000256479,0.00003419229,0.0001591728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2756939,"threshold_uncertainty_score":0.9999939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02910037535194744,"score_gpt":0.3370686540691778,"score_spread":0.3079682787172304,"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."}}