{"id":"W4393492097","doi":"10.5281/zenodo.4016945","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; Software engineering; Software; Programming language; Natural language processing; History; 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":[0.002491808,0.002456252,0.001133078,0.004503433,0.001386068,0.001787284,0.002585376,0.00292516,0.007175923],"category_scores_gemma":[0.008511183,0.0004310583,0.001304915,0.003158738,0.0006121236,0.002038498,0.002992135,0.00179818,0.0101216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002509909,"about_ca_system_score_gemma":0.002037399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02902449,"about_ca_topic_score_gemma":0.05909712,"domain_scores_codex":[0.9967756,0.0009197305,0.0003117278,0.0008247233,0.0008524421,0.0003158975],"domain_scores_gemma":[0.9952208,0.001791079,0.0003859211,0.0008901397,0.001139815,0.0005722464],"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":[0.001433306,0.001063527,0.01139092,0.003097513,0.0002759098,0.0003159762,0.0006433009,0.004119404,0.002764966,0.002833451,0.9331788,0.03888281],"study_design_scores_gemma":[0.001430081,0.0006851736,0.1012344,0.001074026,0.0003339505,0.0009318445,0.002423341,0.03142844,0.007638258,0.004949145,0.847618,0.0002534678],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03323788,0.0009635091,0.002079824,0.0006201167,0.0001819729,0.0003208159,0.9535186,0.00332258,0.005754761],"genre_scores_gemma":[0.006854245,0.00007198023,0.001924595,0.0000766276,0.0000121792,0.0002485819,0.9897832,0.00005951395,0.0009690254],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02902449,"threshold_uncertainty_score":0.05771106,"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."}}