{"id":"W6941119923","doi":"10.13021/orc2020/pdsap7","title":"Replication Data for \"The Mason-Alberta Phonetic Segmenter: A forced alignment system based on deep neural networks and interpolation\"","year":2023,"lang":"en","type":"dataset","venue":"George Mason University","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Replication (statistics); Process (computing); Code (set theory); Artificial neural network; tar (computing); Test data; Data file","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002662153,0.0002107877,0.0001981501,0.00003085347,0.0005053531,0.00008890945,0.0007672133,0.00017086,0.0002591534],"category_scores_gemma":[0.0001181108,0.00009790644,0.00007756476,0.0002227021,0.0000123786,0.00009064574,0.0003134628,0.0001971185,0.00009420521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008180293,"about_ca_system_score_gemma":0.000006329594,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009857014,"about_ca_topic_score_gemma":0.007693083,"domain_scores_codex":[0.9986779,0.0001095627,0.0001641185,0.0006471103,0.0001551059,0.000246195],"domain_scores_gemma":[0.9958178,0.003298346,0.0001969776,0.0005574498,0.00004141079,0.00008802963],"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":[0.0002379099,0.00002538998,0.0001808838,0.00004122285,0.0000377916,0.000004874343,0.000004531523,0.0004159226,0.00002746818,0.00006010954,0.9977635,0.001200444],"study_design_scores_gemma":[0.00007706389,0.0001032682,0.0001731206,0.00007420134,0.0001124691,0.000005425668,0.0001959558,0.3658349,8.757382e-7,0.000001346854,0.6332907,0.0001307002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003827277,0.00005127715,0.0005417369,0.001024247,0.0006549404,0.0007981543,0.996419,0.00005438735,0.00007353638],"genre_scores_gemma":[0.005220538,0.0002037164,0.00001776229,0.0001915089,0.0002275966,0.00001000533,0.9934223,0.000002002577,0.0007046122],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3654189,"threshold_uncertainty_score":0.9967364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01898399764203897,"score_gpt":0.210494369003419,"score_spread":0.19151037136138,"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."}}