{"id":"W3205700046","doi":"10.1109/smartiot52359.2021.00060","title":"Machine Learning-as-a-Service Performance Evaluation on Multi-class Datasets","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Machine learning; Cloud computing; Artificial intelligence; Class (philosophy); Table (database); Service (business); IBM; Process (computing); Service provider; Data science; Data mining; Operating system","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":[0.0008421577,0.0001446288,0.000114973,0.00008054444,0.0002538571,0.000208276,0.0006064378,0.0000607501,0.0004064231],"category_scores_gemma":[0.0004408095,0.0001289025,0.00002792812,0.0005472076,0.00001189178,0.0005451344,0.0002631133,0.0003474612,0.001978517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005592437,"about_ca_system_score_gemma":0.0001656017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001527384,"about_ca_topic_score_gemma":0.0001192788,"domain_scores_codex":[0.9981186,0.0003149848,0.0002054852,0.0005726562,0.0005754105,0.0002128203],"domain_scores_gemma":[0.9984769,0.0001088089,0.0001041969,0.000982839,0.0002360322,0.00009124644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004132649,0.0007511495,0.009775503,0.00008562198,0.00004778002,0.00002654888,0.000774915,0.02760631,0.004904199,0.06607876,0.007434345,0.8824735],"study_design_scores_gemma":[0.0005344224,0.00007101592,0.01716201,0.00001681286,0.000007540732,0.00001346892,0.00001909015,0.8963597,0.001517221,0.00006169864,0.08408269,0.0001542638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2858084,0.001206507,0.4615695,0.07745925,0.002622881,0.001466416,0.0002155257,0.003180348,0.1664712],"genre_scores_gemma":[0.9725074,0.0001020299,0.01636987,0.004473423,0.00006097098,0.00003072389,0.003198221,0.00001475834,0.003242622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8823193,"threshold_uncertainty_score":0.9987985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0474917778370254,"score_gpt":0.3144535249562416,"score_spread":0.2669617471192162,"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."}}