{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002647177,0.0001883503,0.0002972651,0.0004242025,0.0004229628,0.0004644117,0.002070757,0.0001095734,0.0003795879],"category_scores_gemma":[0.001021006,0.0002044148,0.00007445124,0.0006819349,0.00003711151,0.0004335239,0.001652724,0.0005730893,0.0006763228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003434216,"about_ca_system_score_gemma":0.000007771956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002664289,"about_ca_topic_score_gemma":0.000004615556,"domain_scores_codex":[0.9984784,0.00004555243,0.0003862798,0.0004281182,0.0003427178,0.0003189031],"domain_scores_gemma":[0.9988705,0.0001408198,0.0002266798,0.0004769805,0.0001839661,0.0001010884],"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":[0.00002811269,0.00007278661,0.000001109275,0.0004271753,0.00003909774,0.00001141993,0.001853409,0.0002575309,0.0001686328,0.0006909495,0.9940565,0.002393269],"study_design_scores_gemma":[0.0004083623,0.0001843994,0.0000241159,0.0002654736,0.00001369695,0.00002942567,0.0008441701,0.02099135,0.0001836258,0.00005363134,0.9767536,0.0002481588],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003676716,0.0002097015,0.2813593,0.0003571993,0.0006396191,0.001004282,0.7150522,0.0008190281,0.0001910321],"genre_scores_gemma":[0.04067346,0.00002477366,0.003700065,0.000103835,0.00014832,2.080603e-7,0.9546804,0.0006399328,0.00002897337],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2776592,"threshold_uncertainty_score":0.8692987,"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."}}