{"id":"W4287671547","doi":"10.5281/zenodo.3524521","title":"A Comparison of Natural Language Understanding Services for Software Bots","year":2020,"lang":"en","type":"article","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; Software engineering; Natural language processing; Programming language; History","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":[0.0001689313,0.00009646585,0.0001445593,0.00009921413,0.0008293477,0.0004856985,0.001452573,0.00003500962,0.0005953294],"category_scores_gemma":[0.000254981,0.0001019902,0.0000546661,0.0004949988,0.00004417967,0.0005197571,0.001060205,0.0001767804,0.0005602909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009277534,"about_ca_system_score_gemma":0.000003321421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001107133,"about_ca_topic_score_gemma":0.000001026058,"domain_scores_codex":[0.9988891,0.00009665111,0.0002269161,0.0003084072,0.0002587912,0.0002201232],"domain_scores_gemma":[0.9990799,0.00007880174,0.0001432038,0.0002800132,0.0003048919,0.0001132203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006385307,0.0009642048,0.0003315656,0.003449663,0.0005387617,0.000041688,0.2441878,0.001822034,0.07331293,0.1183118,0.2601464,0.2962547],"study_design_scores_gemma":[0.001833024,0.001131031,0.000638702,0.0002821323,0.00005178249,0.00007423035,0.02639823,0.307256,0.01013841,0.001116013,0.6504195,0.0006609348],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01761828,0.0002140644,0.9708672,0.003955218,0.0002077529,0.000502636,0.0001226566,0.001270691,0.005241506],"genre_scores_gemma":[0.9921556,0.000003374584,0.006777353,0.0003859573,0.00007654906,3.919904e-8,0.0002486304,0.0002970879,0.00005544441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745373,"threshold_uncertainty_score":0.7201592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08525610431880891,"score_gpt":0.3161836927182475,"score_spread":0.2309275883994386,"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."}}