{"id":"W4393639961","doi":"10.5281/zenodo.4016894","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Natural (archaeology); Programming language; Software engineering; Software; Natural language; Natural language processing; Geography; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001889028,0.002332663,0.00095024,0.003780286,0.001356944,0.001427577,0.002499112,0.002324738,0.01073054],"category_scores_gemma":[0.006535682,0.0003949532,0.001240471,0.002339738,0.0006017531,0.001892728,0.002819797,0.001766472,0.01827619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001864702,"about_ca_system_score_gemma":0.001940248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0302625,"about_ca_topic_score_gemma":0.07608488,"domain_scores_codex":[0.9977658,0.0006334443,0.0002293818,0.0006190368,0.0005141695,0.0002381361],"domain_scores_gemma":[0.9963996,0.001286488,0.0002229802,0.000766446,0.0008864515,0.0004380271],"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":[0.000944734,0.0008004135,0.006293846,0.002312674,0.0001806745,0.0002416454,0.0004320883,0.003423122,0.002471107,0.001649845,0.9408576,0.04039244],"study_design_scores_gemma":[0.00117061,0.0006209047,0.06323817,0.001042213,0.0002680347,0.0008515274,0.00202147,0.03610612,0.008306654,0.004451009,0.8816975,0.0002257623],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02945661,0.001102034,0.002712694,0.0005704279,0.000304604,0.0003512503,0.9519076,0.006324704,0.007270008],"genre_scores_gemma":[0.0070738,0.00007832133,0.002120829,0.00008413396,0.00001531574,0.0002294597,0.9887536,0.00008471018,0.001559832],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0302625,"threshold_uncertainty_score":0.06017268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06982191414102129,"score_gpt":0.3061113920230067,"score_spread":0.2362894778819854,"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."}}