{"id":"W3196070880","doi":"10.48550/arxiv.2111.05196","title":"NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Utterance; Set (abstract data type); Spoken language; Simple (philosophy); Natural language; Natural language processing; Semantics (computer science); Natural language understanding; Artificial intelligence; Speech recognition; 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":[0.0003382836,0.0001062795,0.0001161223,0.00007010025,0.0001193592,0.0000668009,0.000530707,0.00008861071,0.00002882246],"category_scores_gemma":[0.0001784704,0.0001167405,0.00008397087,0.0003919739,0.00002418305,0.0004600862,0.0001524777,0.0001781227,0.00001384839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001274463,"about_ca_system_score_gemma":0.0001851891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004317266,"about_ca_topic_score_gemma":0.0001351297,"domain_scores_codex":[0.9989276,0.00009063614,0.00009940968,0.0005430322,0.0001306608,0.000208671],"domain_scores_gemma":[0.9989112,0.0001352447,0.00006099581,0.0005379823,0.0002978859,0.00005670033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005879247,0.0001154408,0.003133563,0.0000899688,0.0001042939,0.0004739637,0.001430405,0.06504736,0.004231614,0.8863827,0.001583614,0.03734827],"study_design_scores_gemma":[0.0005640028,0.00001405204,0.001866092,0.00001800676,0.00003242372,0.000009499968,0.0001453459,0.9824539,0.001409123,0.01260373,0.0007180048,0.0001658485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4380358,0.0003777805,0.5579766,0.0004573003,0.0007167578,0.0001885254,0.000004608007,0.0001105456,0.002132051],"genre_scores_gemma":[0.992394,0.00001193203,0.005576688,0.0003320907,0.00009833716,0.000001114081,0.00001712907,0.000006197821,0.00156256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9174065,"threshold_uncertainty_score":0.476054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05376264222521476,"score_gpt":0.2216626485356336,"score_spread":0.1679000063104188,"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."}}