{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01475107,0.00130047,0.0008817465,0.003991779,0.0009429245,0.002839735,0.001472553,0.001185274,0.003044318],"category_scores_gemma":[0.06126928,0.0005191703,0.0008308751,0.002031861,0.001451559,0.002593996,0.003479251,0.00128905,0.003303407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006357185,"about_ca_system_score_gemma":0.001161213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005054434,"about_ca_topic_score_gemma":0.0111526,"domain_scores_codex":[0.9886856,0.002859969,0.001650019,0.003704681,0.002537615,0.0005620529],"domain_scores_gemma":[0.9572265,0.0171441,0.003135535,0.005761019,0.01597999,0.0007528529],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001785026,0.0003501271,0.2907631,0.001985793,0.001241944,0.000767812,0.0146531,0.008923571,0.1083106,0.003724147,0.02262485,0.5448699],"study_design_scores_gemma":[0.0001305195,0.0007220926,0.7899324,0.0005310543,0.0004256647,0.001217312,0.006680864,0.08532684,0.05658808,0.005905845,0.05204812,0.0004912101],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7238622,0.001340017,0.2428414,0.0004584251,0.0004896415,0.0007116952,0.009268178,0.009734862,0.01129364],"genre_scores_gemma":[0.7895129,0.0003411206,0.1790749,0.0002181426,0.0001365912,0.00174043,0.02145376,0.002832402,0.004689896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9852489,"threshold_uncertainty_score":0.07801211,"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."}}