{"id":"W4380785793","doi":"10.1044/2023_jslhr-22-00343","title":"Reproducible Speech Research With the Artificial Intelligence–Ready PERCEPT Corpora","year":2023,"lang":"en","type":"article","venue":"Journal of Speech Language and Hearing Research","topic":"Language Development and Disorders","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Deafness and Other Communication Disorders; Syracuse University; National Science Foundation","keywords":"Percept; Computer science; Perception; Natural language processing; Psychology; Speech recognition","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":[0.01573289,0.0001443917,0.0002700077,0.001055463,0.0006041254,0.0002881832,0.000552482,0.0001293736,0.001463087],"category_scores_gemma":[0.0006323351,0.00008563149,0.00005918208,0.002153547,0.0005287181,0.0001589162,0.0002669972,0.001853583,0.0007154316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007060063,"about_ca_system_score_gemma":0.0002441666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001276718,"about_ca_topic_score_gemma":0.000362843,"domain_scores_codex":[0.9960666,0.0005598223,0.0004313362,0.0004243891,0.001618534,0.0008992611],"domain_scores_gemma":[0.9974724,0.0008479273,0.0001076018,0.000585496,0.0007911967,0.0001954016],"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":[0.001296549,0.0002707558,0.01115734,0.00009521443,0.0002292508,0.009254727,0.126602,0.000009517251,0.008130388,0.004453226,0.0716376,0.7668635],"study_design_scores_gemma":[0.0009333353,0.00219422,0.06474389,0.0003262415,0.00004209202,0.002162433,0.8813674,0.00007266492,0.01154323,0.008736302,0.02734982,0.0005283884],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9761009,0.001457642,0.00002214558,0.007327786,0.0002006532,0.0003309155,0.000002439014,0.00003795032,0.01451959],"genre_scores_gemma":[0.9815619,0.0003017825,0.0006551137,0.00007746886,0.001098153,0.00001605839,0.000007329973,0.00004265044,0.01623956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7663351,"threshold_uncertainty_score":0.9994497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2996275926697824,"score_gpt":0.4804863928005842,"score_spread":0.1808588001308019,"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."}}