{"id":"W4401021697","doi":"10.1145/3680470","title":"Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Green IT and Sustainability","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Energy consumption; Granularity; Energy accounting; Energy (signal processing); Efficient energy use; Instrumentation (computer programming); Deep learning; Work (physics); Artificial intelligence; Operating system; Mechanical engineering; Electrical engineering; Engineering","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":[0.0008134051,0.0002984579,0.0003770162,0.000337419,0.00008961453,0.00003796951,0.0001458422,0.0002230815,0.00003173832],"category_scores_gemma":[0.000558004,0.0003129406,0.0001057361,0.0004625571,0.00003165285,0.0001488775,0.000009901659,0.0004909628,0.000001923954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228828,"about_ca_system_score_gemma":0.00004183169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003119505,"about_ca_topic_score_gemma":0.0006913448,"domain_scores_codex":[0.9984671,0.0001805897,0.0003367559,0.0003918935,0.0001719855,0.0004516021],"domain_scores_gemma":[0.9985158,0.001035033,0.00001257105,0.0002956301,0.00005480354,0.00008619567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002620326,0.00003042458,0.0001544488,0.0006217302,0.0001594089,0.00006308006,0.002129791,0.712135,0.004656971,0.00129699,0.00001058271,0.2787153],"study_design_scores_gemma":[0.002889175,0.0008660108,0.003863919,0.001647743,0.000483889,0.0003866239,0.002905412,0.6998631,0.135271,0.01900661,0.1288884,0.003928078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01693841,0.004149367,0.9766953,0.00006894893,0.0009306287,0.00005904874,0.000003046707,0.001129725,0.0000255428],"genre_scores_gemma":[0.8920755,0.0003594568,0.1071647,0.00002316919,0.00007129956,0.0001216849,0.000005861692,0.00007420513,0.0001041879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.875137,"threshold_uncertainty_score":0.9999323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05270298121953904,"score_gpt":0.2806003900837206,"score_spread":0.2278974088641816,"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."}}