{"id":"W836999996","doi":"10.18653/v1/w15-4640","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Samsung Advanced Institute of Technology","keywords":"Computer science; Benchmark (surveying); Dialog box; Microblogging; Task (project management); Artificial intelligence; Natural language processing; Social media; Resource (disambiguation); World Wide Web; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01238938,0.000611449,0.0009626894,0.0006000279,0.000530856,0.002024359,0.00635343,0.0008811076,0.000002216832],"category_scores_gemma":[0.001408938,0.0004101204,0.000207491,0.000839163,0.0002440145,0.0003370965,0.005049957,0.00163434,0.000158525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005258637,"about_ca_system_score_gemma":0.001634789,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01046779,"about_ca_topic_score_gemma":0.01892463,"domain_scores_codex":[0.9920385,0.001735759,0.001215076,0.001775929,0.001352217,0.001882511],"domain_scores_gemma":[0.9921694,0.001961582,0.0004377184,0.004046627,0.0008813718,0.0005032899],"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":[0.0004001347,0.000575435,0.001687207,0.001415675,0.0003041461,0.0002632014,0.003669957,0.001997756,0.0001695287,0.1370919,0.8447962,0.007628877],"study_design_scores_gemma":[0.007248491,0.0003792931,0.0008449552,0.0007268167,0.00003228944,0.0001055222,0.001185308,0.3114007,0.0002322189,0.0541676,0.6217904,0.0018864],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003963543,0.01827946,0.7989421,0.004136971,0.06213748,0.02674571,0.08165095,0.001079396,0.00306443],"genre_scores_gemma":[0.9321078,0.0004917678,0.02006792,0.0004047749,0.004074057,0.006097849,0.03513567,0.0001902687,0.00142988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9281443,"threshold_uncertainty_score":0.9998351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1752930382556378,"score_gpt":0.3902715041426384,"score_spread":0.2149784658870007,"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."}}