{"id":"W4393876881","doi":"10.5281/zenodo.4016881","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); Natural language; Programming language; Software engineering; Software; 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":[0.001787502,0.002230111,0.0009411335,0.003749877,0.001267752,0.001356934,0.002156478,0.001916289,0.01225143],"category_scores_gemma":[0.005621094,0.0003639971,0.001212903,0.002215449,0.0005433754,0.001795303,0.002387546,0.00157756,0.01843631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00158369,"about_ca_system_score_gemma":0.001480186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01793048,"about_ca_topic_score_gemma":0.04661898,"domain_scores_codex":[0.9978324,0.0006120536,0.0002232202,0.0005981521,0.0005166025,0.0002175682],"domain_scores_gemma":[0.9962977,0.001455852,0.0002372867,0.0007761989,0.0008276238,0.0004054674],"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":[0.001402255,0.001166668,0.007559882,0.002726544,0.0002136014,0.0002513369,0.0004183302,0.003625598,0.002523449,0.001894828,0.9294406,0.04877695],"study_design_scores_gemma":[0.001410263,0.001013785,0.08161285,0.001168421,0.0003251486,0.001077356,0.002329821,0.04110995,0.01027407,0.004716024,0.8547028,0.0002596295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03838293,0.001316964,0.002760728,0.0005005853,0.0003262426,0.0003504818,0.9411383,0.00650195,0.008721774],"genre_scores_gemma":[0.009554941,0.0000954566,0.002244177,0.00008399034,0.00001758875,0.0002258392,0.9858512,0.00009577091,0.001831093],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01793048,"threshold_uncertainty_score":0.04098517,"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."}}