{"id":"W4402666573","doi":"10.3758/s13428-024-02493-2","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada; James S. McDonnell Foundation; Academy of Finland; Horizon 2020 Framework Programme; Directorate for Engineering; Grand Équipement National De Calcul Intensif; China Scholarship Council; Economic and Social Research Council; European Commission; National Institutes of Health; National Science Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Computer science; Variation (astronomy); Reliability (semiconductor); Intraclass correlation; Natural language processing; Language acquisition; Identity (music); Artificial intelligence; Psychology; Developmental psychology; Mathematics education; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02285436,0.0001662852,0.0003140652,0.000360771,0.0003019365,0.0003311561,0.0005875236,0.0001729284,0.001096747],"category_scores_gemma":[0.006394414,0.00008877476,0.0001224543,0.001981909,0.0007451643,0.0002915776,0.0003758471,0.001107637,0.00001189953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009096744,"about_ca_system_score_gemma":0.0001553548,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00951278,"about_ca_topic_score_gemma":0.0001273088,"domain_scores_codex":[0.9946533,0.003186302,0.0004980467,0.0005081879,0.000647505,0.0005066411],"domain_scores_gemma":[0.9870173,0.01179432,0.00008406171,0.0007068301,0.0003010608,0.0000964263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003346613,0.0001557977,0.02378611,0.0000603238,0.00006453274,0.00006303954,0.01530209,8.647892e-7,0.003735694,0.0007666855,0.002666425,0.9530638],"study_design_scores_gemma":[0.008275556,0.0003485288,0.7809694,0.0006904294,0.001361401,0.0001424575,0.06925803,0.010536,0.01490215,0.03143126,0.08045401,0.001630801],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9669515,0.009892538,0.01786656,0.0009156057,0.0008765538,0.0009426973,0.00003233765,0.00007246181,0.002449754],"genre_scores_gemma":[0.9092818,0.0005110612,0.08617619,0.00008756921,0.0002846221,0.0002525465,0.00003832267,0.00007956305,0.003288314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9514329,"threshold_uncertainty_score":0.9998164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2585887042868682,"score_gpt":0.5697168966099126,"score_spread":0.3111281923230445,"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."}}