{"id":"W7125580712","doi":"10.1109/cascon66301.2025.00056","title":"Energy Consumption Analysis of Large Language Models Across CPU and GPU Using Diverse Metric Types","year":2025,"lang":"","type":"article","venue":"","topic":"Big Data and Digital Economy","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Energy consumption; Metric (unit); Efficient energy use; Energy (signal processing); Construct (python library); Key (lock); Range (aeronautics); Implementation","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":[0.001481535,0.0009785537,0.0006932975,0.001252713,0.0005485718,0.001226571,0.001448902,0.0006564982,0.001963822],"category_scores_gemma":[0.008431747,0.0003906651,0.001078628,0.002378374,0.0004868411,0.002391549,0.000598881,0.001109136,0.0005676078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00172055,"about_ca_system_score_gemma":0.00146046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01827884,"about_ca_topic_score_gemma":0.02604809,"domain_scores_codex":[0.9988139,0.0003442565,0.0001045584,0.0002249082,0.0003779159,0.0001345809],"domain_scores_gemma":[0.9953043,0.003136398,0.0001987477,0.0005776114,0.0006803525,0.0001026421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0005209654,0.0003273325,0.01518035,0.0002862348,0.0001935702,0.0001741903,0.0002132967,0.8878008,0.006085368,0.004908988,0.005996936,0.07831198],"study_design_scores_gemma":[0.000009129401,0.00004956419,0.001438645,0.000005243454,0.00001325927,0.00001878425,0.00004407175,0.993521,0.003042693,0.001324274,0.000522845,0.00001054557],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8376743,0.001339516,0.1427224,0.0009194604,0.0001521973,0.0001393868,0.002441673,0.007292269,0.007318703],"genre_scores_gemma":[0.9482894,0.0002992621,0.04631236,0.000128419,0.00001711335,0.000141079,0.002798478,0.0005553088,0.001458536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01827884,"threshold_uncertainty_score":0.03634489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04797013277112624,"score_gpt":0.3153490544891729,"score_spread":0.2673789217180467,"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."}}