{"id":"W3098826124","doi":"10.1109/taslp.2024.3426331","title":"Overview of the Ninth Dialog System Technology Challenge: DSTC9","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dialog box; Computer science; Task (project management); Dialog system; Domain (mathematical analysis); Set (abstract data type); Human–computer interaction; Natural language processing; Artificial intelligence; Multimedia; World Wide Web; Programming language; Engineering","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":[0.0002981193,0.0002126222,0.0002897031,0.0003189114,0.000246036,0.0001938267,0.0007835147,0.0001665873,0.00001162292],"category_scores_gemma":[0.00002644368,0.0001475141,0.0001232672,0.001152235,0.0001199482,0.0002953536,0.00002619496,0.0003512531,0.00002828596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007003207,"about_ca_system_score_gemma":0.0001678468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007286152,"about_ca_topic_score_gemma":0.00007902964,"domain_scores_codex":[0.9985126,0.00007128005,0.0003226589,0.0004759504,0.0003053362,0.000312138],"domain_scores_gemma":[0.9989304,0.00008215886,0.00009772051,0.0007420306,0.00006622347,0.00008145355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001066753,0.00006905742,0.00001896073,0.001700653,0.00005221995,0.00009265519,0.002578842,0.00003076668,0.006331667,0.001870447,0.0000681932,0.9871759],"study_design_scores_gemma":[0.003331736,0.001277214,0.000607836,0.02065417,0.0005244942,0.004279131,0.01089976,0.05371408,0.8774562,0.01207268,0.01243871,0.002744037],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03947695,0.1028082,0.8404709,0.005185809,0.003619721,0.0008672624,0.0000538957,0.001862466,0.005654821],"genre_scores_gemma":[0.9931439,0.0002274336,0.006078796,0.00007304309,0.0001112187,0.00003796387,7.322367e-7,0.00002110787,0.0003057959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9844319,"threshold_uncertainty_score":0.6015449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02095451411627129,"score_gpt":0.2734351245595172,"score_spread":0.2524806104432459,"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."}}