{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002325213,0.0001242454,0.0001222598,0.0001953625,0.0002500115,0.000190275,0.0005110595,0.00001981378,0.00004592007],"category_scores_gemma":[0.00002442812,0.0001075695,0.00002914913,0.0009220495,0.00001078466,0.0005562202,0.0001846412,0.0001147538,0.0004480162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006785378,"about_ca_system_score_gemma":0.00005066146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002673342,"about_ca_topic_score_gemma":0.0006781393,"domain_scores_codex":[0.998763,0.00007726257,0.0001978539,0.0004082498,0.0003256201,0.0002279945],"domain_scores_gemma":[0.9990722,0.0001180111,0.00005978148,0.0005487565,0.0001296203,0.00007162991],"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":[0.0001407639,0.01242821,0.2125658,0.0002585889,0.0006649715,0.05349938,0.1741235,0.4793759,0.001716523,0.01788469,0.02776592,0.01957581],"study_design_scores_gemma":[0.000416626,0.0002454861,0.001077333,0.00001948459,0.000004920532,0.00007691086,0.00668392,0.989933,0.001179878,0.0001438763,0.00007110451,0.0001474895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8706651,0.000001025657,0.1195085,0.001213189,0.0004532346,0.0004507146,7.232411e-7,0.0007489446,0.006958573],"genre_scores_gemma":[0.9952688,1.357547e-7,0.003123634,0.0009982233,0.00004788447,0.0001328076,0.000001680447,0.000009261576,0.0004176203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5105571,"threshold_uncertainty_score":0.5758491,"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."}}