{"id":"W4393555139","doi":"10.5281/zenodo.4016870","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; Software engineering; Natural (archaeology); Natural language; Software; Programming 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":[0.001849273,0.002351231,0.0009546903,0.003725749,0.001254097,0.00137982,0.002313664,0.002210394,0.01072],"category_scores_gemma":[0.006017686,0.0003657642,0.001251488,0.002158232,0.0005591694,0.001867018,0.002680965,0.001645246,0.01709995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001767912,"about_ca_system_score_gemma":0.001790443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02558086,"about_ca_topic_score_gemma":0.06394618,"domain_scores_codex":[0.9977915,0.0006153205,0.0002240364,0.0006230317,0.0005110282,0.0002350316],"domain_scores_gemma":[0.9966872,0.001160586,0.000222931,0.0007327045,0.0008037991,0.0003928671],"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":[0.001094089,0.0009365247,0.006835992,0.002528812,0.0001958681,0.0002486029,0.0004325549,0.004099059,0.002753024,0.001815985,0.9295287,0.04953078],"study_design_scores_gemma":[0.001101421,0.0007165041,0.06180696,0.001148266,0.0002757103,0.0008626647,0.00197503,0.04247171,0.009878499,0.004784884,0.8747482,0.0002300245],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03389585,0.00128666,0.003159034,0.0005963092,0.0003514435,0.0003720273,0.9452673,0.007414062,0.00765739],"genre_scores_gemma":[0.008049575,0.0000905189,0.002508668,0.00008517562,0.00001675875,0.0002262316,0.9872644,0.00009407272,0.001664628],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02558086,"threshold_uncertainty_score":0.05086392,"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."}}