{"id":"W2805828232","doi":"10.1007/s10664-018-9629-2","title":"What can Android mobile app developers do about the energy consumption of machine learning?","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Green IT and Sustainability","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Alberta","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Android (operating system); Energy consumption; Implementation; Facial recognition system; Multimedia; Feature extraction; Software engineering; Operating system; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002172495,0.0002221446,0.0002450875,0.00008174524,0.000100892,0.00006526616,0.000214767,0.0001212339,0.0001547754],"category_scores_gemma":[0.0002279613,0.0001767351,0.00008524151,0.00029493,0.0001086219,0.00016281,0.00006975102,0.0002798371,0.00001189983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001428366,"about_ca_system_score_gemma":0.00002787871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004448331,"about_ca_topic_score_gemma":0.00003895847,"domain_scores_codex":[0.99889,0.00003096258,0.0002947643,0.0002079648,0.0002081098,0.0003681307],"domain_scores_gemma":[0.9992586,0.0002222483,0.00003126569,0.0002684932,0.0001079742,0.0001114552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004951037,0.00008102103,0.5245548,0.0007695589,0.0002714078,0.00002267845,0.008665725,0.3925394,0.001307631,0.0001618655,0.001887419,0.06968897],"study_design_scores_gemma":[0.001531358,0.0005472779,0.2746798,0.0004096765,0.0001154108,0.00007373177,0.001125838,0.300677,0.01825181,0.0001923513,0.4004335,0.001962233],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9418951,0.003248714,0.05326625,0.00003566625,0.0006622068,0.0001550472,0.000006965699,0.0006849961,0.0000450201],"genre_scores_gemma":[0.9985456,0.0002528513,0.0007947812,0.00003890895,0.0001408936,0.00004899888,0.00001393212,0.00004919068,0.0001147791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3985461,"threshold_uncertainty_score":0.7207047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01064170486006739,"score_gpt":0.2364697327071582,"score_spread":0.2258280278470909,"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."}}