{"id":"W4292829073","doi":"10.1109/cvprw56347.2022.00410","title":"MAPLE-Edge: A Runtime Latency Predictor for Edge Devices","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Latency (audio); Edge device; Enhanced Data Rates for GSM Evolution; Maple; Artificial neural network; Artificial intelligence; Computer architecture; Parallel computing; Operating system; Cloud computing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003980564,0.0004619346,0.0004408287,0.0002904989,0.001027272,0.0004383515,0.001161951,0.0001243875,0.0007477772],"category_scores_gemma":[0.00001299148,0.0004584102,0.0001756511,0.0007363881,0.00007816821,0.0005575056,0.0007442636,0.0006345771,0.0001559447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008194643,"about_ca_system_score_gemma":0.00007463253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006933964,"about_ca_topic_score_gemma":0.0000187132,"domain_scores_codex":[0.9965949,0.0002761402,0.0006191457,0.001316924,0.0005870619,0.0006058114],"domain_scores_gemma":[0.9977556,0.0005742979,0.000361895,0.0007653479,0.0002494333,0.00029345],"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":[0.00008519834,0.00033723,0.0002939921,0.0000570886,0.00004322956,0.00002114409,0.0005388898,0.00041178,0.0003409987,0.001221396,0.02289527,0.9737538],"study_design_scores_gemma":[0.002582232,0.001743199,0.004798889,0.0003365964,0.00005594137,0.0001319668,0.0001145187,0.9262391,0.0003815573,0.01694462,0.04532731,0.001344021],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04981278,0.0001495222,0.9409229,0.003928106,0.002477384,0.001461379,0.0002812567,0.0005150411,0.0004516154],"genre_scores_gemma":[0.9696296,0.0002332466,0.02079768,0.005960918,0.0007013745,0.001338356,0.0004543823,0.00006661555,0.0008178081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9724098,"threshold_uncertainty_score":0.9997867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04519587777785523,"score_gpt":0.2886597728719205,"score_spread":0.2434638950940652,"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."}}