{"id":"W4391093745","doi":"10.1109/bigdata59044.2023.10386251","title":"Comparing Generative Chatbots Based on Process Requirements: A Case Study","year":2023,"lang":"en","type":"article","venue":"","topic":"AI in Service Interactions","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Computer science; Process (computing); Software engineering; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01118842,0.0009123581,0.0007119271,0.001702986,0.001479038,0.002202386,0.002555367,0.00290019,0.00338392],"category_scores_gemma":[0.06113976,0.0004949506,0.0009149872,0.001566661,0.001567685,0.0032345,0.002629126,0.002119776,0.001177505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002117276,"about_ca_system_score_gemma":0.001352497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004601169,"about_ca_topic_score_gemma":0.005661843,"domain_scores_codex":[0.9893572,0.007900938,0.0005654834,0.0007144182,0.001069232,0.0003927584],"domain_scores_gemma":[0.8868498,0.09791233,0.002582461,0.005841032,0.005198615,0.00161584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.009540346,0.01237531,0.08041613,0.008468605,0.0006704399,0.01381493,0.09798271,0.2369527,0.04305289,0.07901919,0.01562483,0.4020818],"study_design_scores_gemma":[0.00149976,0.007515255,0.05433791,0.001142074,0.0005633867,0.003735933,0.04915347,0.7461204,0.03446972,0.04513657,0.05576847,0.0005570015],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9202267,0.0004453782,0.06795786,0.0005302744,0.00006292719,0.001155449,0.000488909,0.00110679,0.008025762],"genre_scores_gemma":[0.9491163,0.0002029597,0.04630944,0.0002022546,0.00002392527,0.0007600735,0.0007864721,0.0001869654,0.002411612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01118842,"threshold_uncertainty_score":0.05917072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1369990395132718,"score_gpt":0.3919133358097079,"score_spread":0.2549142962964361,"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."}}