{"id":"W4412732703","doi":"10.3389/fpsyt.2025.1451368","title":"A software pipeline for systematizing machine learning of speech data","year":2025,"lang":"en","type":"article","venue":"Frontiers in Psychiatry","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Pipeline (software); Computer science; Software; Artificial intelligence; Natural language processing; Machine learning; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.000591351,0.0001181815,0.0003033329,0.0003598769,0.00005775257,0.00001041879,0.0003238244,0.0001375901,0.00007512421],"category_scores_gemma":[0.0001955165,0.0001187626,0.00006792735,0.0003169125,0.00003007467,0.00006792191,0.00006555496,0.000213936,0.000009854773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002426647,"about_ca_system_score_gemma":0.00005387396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004432337,"about_ca_topic_score_gemma":0.00007426122,"domain_scores_codex":[0.9987788,0.0001229727,0.0004696534,0.0003458693,0.00008634947,0.0001963965],"domain_scores_gemma":[0.9991913,0.00006131984,0.000175369,0.0004895782,0.00005426787,0.00002810012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002621506,0.0002547532,0.211339,0.001631666,0.0001638513,0.000001906953,0.000385317,0.00001836487,0.00001378786,0.002927155,0.6596399,0.1233621],"study_design_scores_gemma":[0.05389887,0.001248279,0.06611162,0.01965774,0.002046894,0.0001703724,0.0621522,0.1914261,0.0004613958,0.1291509,0.4702657,0.003409897],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003643069,0.006992552,0.9485708,0.001155313,0.02967302,0.0007360098,0.0001960349,0.0001019892,0.008931228],"genre_scores_gemma":[0.2094978,0.0001391516,0.7683545,0.001216968,0.0007747107,0.0001618169,0.001814962,0.000084509,0.01795563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2058547,"threshold_uncertainty_score":0.4842996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0272898794691758,"score_gpt":0.3251313847293571,"score_spread":0.2978415052601813,"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."}}