{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137869,0.001001401,0.0004963694,0.0006366689,0.0003011548,0.001178404,0.001176642,0.000487485,0.001298803],"category_scores_gemma":[0.005522923,0.0003521602,0.000333321,0.0006518271,0.0005659385,0.003653372,0.001275219,0.001511217,0.0002656195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027453,"about_ca_system_score_gemma":0.001036077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006267202,"about_ca_topic_score_gemma":0.01391244,"domain_scores_codex":[0.9994828,0.0001169636,0.00002793632,0.0001496214,0.0001484024,0.0000743381],"domain_scores_gemma":[0.998541,0.0006762506,0.0001756188,0.0002955956,0.0002406943,0.00007094206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002957919,0.0005169885,0.01549342,0.0002355541,0.000133024,0.00008308852,0.000216724,0.7126799,0.021592,0.008616446,0.003822794,0.2363143],"study_design_scores_gemma":[0.000006709028,0.00003668412,0.0008320543,0.000009851284,0.00001019854,0.000009115171,0.00002079436,0.9859937,0.006145233,0.006038797,0.000886681,0.0000100914],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2088576,0.000607772,0.776474,0.0008064819,0.0000834802,0.00008158309,0.0005404809,0.007815517,0.004733078],"genre_scores_gemma":[0.889053,0.0001810134,0.1089556,0.0002149229,0.00001848052,0.00005434536,0.0004029675,0.0002214891,0.0008983585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006267202,"threshold_uncertainty_score":0.01246142,"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."}}