{"id":"W2985067290","doi":"10.18653/v1/d19-1459","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dialog box; Joint (building); Computer science; Natural language; Natural (archaeology); Natural language processing; Artificial intelligence; Engineering; World Wide Web; History; Architectural engineering; 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":[0.00009908222,0.00005932403,0.0000775869,0.00002998528,0.00002215556,0.00008346606,0.0003478727,0.0000222665,0.00008110291],"category_scores_gemma":[0.00001243003,0.00004890832,0.000009843069,0.00005228063,0.00001233169,0.000276033,0.0004746318,0.00004333318,0.0002124321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008251304,"about_ca_system_score_gemma":0.00001374928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002363805,"about_ca_topic_score_gemma":0.00001742636,"domain_scores_codex":[0.9994,0.00001711606,0.00008341986,0.0002646123,0.0001052643,0.0001296049],"domain_scores_gemma":[0.9993975,0.00003640944,0.00001961557,0.000477026,0.00001050441,0.00005891295],"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":[0.00001541548,0.00008564073,0.01913208,0.0001438046,0.00004223054,0.0001089053,0.002847851,0.0005134972,0.001126715,0.7344674,0.06450532,0.1770112],"study_design_scores_gemma":[0.001435807,0.00018612,0.00763926,0.00003740406,0.00001780854,0.00006819524,0.000160997,0.8906754,0.0002302614,0.01923381,0.07965624,0.0006587485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03480494,0.00003600255,0.9507512,0.001183839,0.0004664641,0.0001779897,0.0001262197,0.000125677,0.01232765],"genre_scores_gemma":[0.9584105,0.000006821672,0.03993301,0.0009265385,0.00003580146,0.000002204923,0.00005801742,0.000003131914,0.0006239655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9236056,"threshold_uncertainty_score":0.2730456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0398766274616048,"score_gpt":0.2522937653920621,"score_spread":0.2124171379304572,"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."}}