{"id":"W4400292625","doi":"10.31234/osf.io/vufw4","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Grand Équipement National De Calcul Intensif; European Commission; China Scholarship Council; National Institutes of Health; National Science Foundation; James S. McDonnell Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Reliability (semiconductor); Computer science; Reliability engineering; Statistics; Mathematics; Engineering; Physics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003329253,0.0002779027,0.0005016287,0.0002248172,0.0001603767,0.001169593,0.001575511,0.0002516117,0.0001284115],"category_scores_gemma":[0.003055424,0.0001414553,0.0002584436,0.0008451719,0.0002373039,0.0003467317,0.003376648,0.001039143,0.0000112772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008805573,"about_ca_system_score_gemma":0.000178055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004623527,"about_ca_topic_score_gemma":0.0001730675,"domain_scores_codex":[0.99749,0.0002842002,0.0007017558,0.0007486742,0.0005401361,0.0002351754],"domain_scores_gemma":[0.9934285,0.004464543,0.0003781925,0.001310169,0.0003428897,0.00007575248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006069406,0.00009613609,0.0007045305,0.0002951452,0.0001634171,0.00001480198,0.002193656,0.00007828385,0.0002191512,0.003394541,0.002581532,0.9901981],"study_design_scores_gemma":[0.0004283477,0.00001120361,0.001965874,0.000476152,0.0002575175,0.00002026334,0.0003035679,0.8250231,0.005166481,0.1646301,0.001314728,0.0004027287],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4442548,0.002322009,0.5320272,0.008016025,0.00264882,0.0009191362,0.00007733167,0.000350766,0.009383861],"genre_scores_gemma":[0.8164559,0.001077532,0.1806924,0.0006979173,0.0003542075,0.00002955376,0.0000152298,0.00003706007,0.0006401853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9897954,"threshold_uncertainty_score":0.9998673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04114783272527828,"score_gpt":0.2719872914437348,"score_spread":0.2308394587184566,"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."}}