{"id":"W4221148028","doi":"10.1007/s11633-022-1387-3","title":"EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training","year":2023,"lang":"en","type":"article","venue":"Machine Intelligence Research","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Open domain; Domain (mathematical analysis); Chatbot; Scale (ratio); Quality (philosophy); Key (lock); Open research; Architecture; Artificial intelligence; Code (set theory); Data science; World Wide Web; Question answering; Computer security","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009343676,0.0002895872,0.0004099479,0.0005794152,0.00079581,0.001365876,0.004652314,0.0001143995,0.00002736415],"category_scores_gemma":[0.0008960524,0.000218645,0.00005670309,0.003955065,0.0002117406,0.0008612627,0.003461541,0.001072219,0.0003646381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001386583,"about_ca_system_score_gemma":0.0004522978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002300331,"about_ca_topic_score_gemma":0.0008532887,"domain_scores_codex":[0.9944117,0.0008231435,0.0005739139,0.001107116,0.001614392,0.001469742],"domain_scores_gemma":[0.9966594,0.00100871,0.0001118786,0.001463185,0.0003454864,0.0004113208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00012566,0.0004824135,0.1416264,0.0009697475,0.0002296846,0.001086008,0.1512805,0.2477172,0.006035572,0.2305424,0.001978136,0.2179263],"study_design_scores_gemma":[0.0001869419,0.0001805828,0.001462182,0.0002716988,0.000001744711,0.00005248455,0.002032626,0.9727296,0.0003416267,0.02151666,0.0009116048,0.0003122369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2086725,0.0002350908,0.7836269,0.001608948,0.0003471008,0.001010899,0.00001404913,0.000444385,0.004040204],"genre_scores_gemma":[0.962186,0.00003571062,0.03592284,0.00008129784,0.0002582273,0.0002836068,0.00002223046,0.00004491113,0.001165209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7535135,"threshold_uncertainty_score":0.9996708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1327379437539389,"score_gpt":0.4119476549633612,"score_spread":0.2792097112094223,"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."}}