{"id":"W4393698367","doi":"10.5281/zenodo.4733028","title":"A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering","year":2020,"lang":"en","type":"dataset","venue":"Figshare","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); Software; Natural language; Software engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002663813,0.0002088796,0.0003617131,0.0002113495,0.00003532038,0.00008364648,0.001066065,0.0001680654,0.00156931],"category_scores_gemma":[0.001082952,0.0002117789,0.0001061379,0.0003332155,0.000002187917,0.0003560568,0.0004359359,0.0004986189,0.0002080705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000195558,"about_ca_system_score_gemma":0.00007338395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001967517,"about_ca_topic_score_gemma":0.0001773064,"domain_scores_codex":[0.9988957,0.000005224387,0.0003251244,0.0003200413,0.0002126007,0.0002412966],"domain_scores_gemma":[0.9986923,0.0006068569,0.0002392903,0.0003589464,0.00004556419,0.00005700426],"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":[0.000004396751,0.00001825439,0.000003198009,0.001110191,0.00001828696,0.00001292991,0.0004722223,0.0001998043,0.000003513315,0.000009419125,0.9980492,0.00009858917],"study_design_scores_gemma":[0.000580706,0.000135282,0.00007799457,0.01231134,0.00001989914,0.0000149146,0.0007386371,0.125851,0.0004299767,0.00004007744,0.8590697,0.0007304575],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000004847689,0.0002682265,0.002312207,0.00003076169,0.0002981718,0.0003212182,0.9966732,0.00008919261,0.000002152313],"genre_scores_gemma":[0.002427998,8.086599e-7,0.002204014,0.00008568913,0.00009792503,0.0001393307,0.9950242,0.00001568965,0.000004358836],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1389795,"threshold_uncertainty_score":0.9993434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09965953655803168,"score_gpt":0.3454661325239714,"score_spread":0.2458065959659397,"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."}}