{"id":"W3167335398","doi":"10.18653/v1/2021.sigtyp-1.11","title":"SIGTYP 2021 Shared Task: Robust Spoken Language Identification","year":2021,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Typology; Computer science; Identification (biology); Task (project management); Natural language processing; Artificial intelligence; Linguistics; History; Engineering; Philosophy; Biology; Archaeology","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":[0.0002135217,0.0001089282,0.0001128243,0.00007404704,0.00008479916,0.000493503,0.000786853,0.00007391387,0.0004394839],"category_scores_gemma":[0.0001703545,0.00009854621,0.00005205518,0.0005932202,0.00001821877,0.0007565556,0.0003534542,0.0001397285,0.0001902589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004346812,"about_ca_system_score_gemma":0.00008459275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004170439,"about_ca_topic_score_gemma":0.00003442153,"domain_scores_codex":[0.99886,0.00005321689,0.0001961071,0.0004370625,0.0002522558,0.0002013803],"domain_scores_gemma":[0.9988918,0.00004280999,0.00007315436,0.0007441938,0.0001879588,0.00006012211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004692327,0.0001563214,0.0002482071,0.00007075386,0.0000330762,0.0006684569,0.002734024,0.00002471285,0.5908337,0.1247155,0.03306688,0.2474437],"study_design_scores_gemma":[0.0002227718,0.00001870439,0.0007830274,0.00006402907,0.00001152757,0.0001013369,0.000253911,0.01792584,0.9632863,0.01326676,0.003605006,0.0004607418],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002607974,0.003424973,0.9869016,0.002123641,0.0002207857,0.00009577031,0.000004989886,0.0007583821,0.003861888],"genre_scores_gemma":[0.3189121,0.00001730564,0.6698973,0.0005354978,0.00009291998,0.00001423821,0.00004860935,0.00001102743,0.01047105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3724526,"threshold_uncertainty_score":0.4812041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01274989262124065,"score_gpt":0.2627833683118665,"score_spread":0.2500334756906258,"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."}}