{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RMNB2P56NRT4HWSQK335ZMSYKM","short_pith_number":"pith:RMNB2P56","schema_version":"1.0","canonical_sha256":"8b1a1d3fbe6c67c3da5056f7dcb258532c837831e0a121c73104c22fba99efd4","source":{"kind":"arxiv","id":"2507.11417","version":1},"attestation_state":"computed","paper":{"title":"Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Miray \\\"Ozcan, Odej Kao, Philipp Wei{\\ss}, Philipp Wiesner","submitted_at":"2025-07-15T15:44:03Z","abstract_excerpt":"The environmental impact of Large Language Models (LLMs) is rising significantly, with inference now accounting for more than half of their total lifecycle carbon emissions. However, existing simulation frameworks, which are increasingly used to determine efficient LLM deployments, lack any concept of power and, therefore, cannot accurately estimate inference-related emissions. We present a simulation framework to assess the energy and carbon implications of LLM inference under varying deployment setups. First, we extend a high-fidelity LLM inference simulator with a GPU power model that estim"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-07-15T15:44:03Z","cross_cats_sorted":[],"title_canon_sha256":"35c32a1633fda9d8ec0c9608dc4ad6917559977ed48155b5824fb2a97537a236","abstract_canon_sha256":"8145b96c1973f04ae694d4d0727eb5bba438c9b2ce5aa10f5ec2af8b0664c99e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:38.914642Z","signature_b64":"KkwLEz2ROwMgCoP9zx1CAOZLcM0DL8wzDnq+g+ouv9+EeEp+wvmx+LF1CWd3sAo9BCv6eTHeVmv6RGl9dvndCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1a1d3fbe6c67c3da5056f7dcb258532c837831e0a121c73104c22fba99efd4","last_reissued_at":"2026-07-05T11:37:38.914116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:38.914116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Miray \\\"Ozcan, Odej Kao, Philipp Wei{\\ss}, Philipp Wiesner","submitted_at":"2025-07-15T15:44:03Z","abstract_excerpt":"The environmental impact of Large Language Models (LLMs) is rising significantly, with inference now accounting for more than half of their total lifecycle carbon emissions. However, existing simulation frameworks, which are increasingly used to determine efficient LLM deployments, lack any concept of power and, therefore, cannot accurately estimate inference-related emissions. We present a simulation framework to assess the energy and carbon implications of LLM inference under varying deployment setups. First, we extend a high-fidelity LLM inference simulator with a GPU power model that estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11417","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.11417/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.11417","created_at":"2026-07-05T11:37:38.914183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11417v1","created_at":"2026-07-05T11:37:38.914183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11417","created_at":"2026-07-05T11:37:38.914183+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMNB2P56NRT4","created_at":"2026-07-05T11:37:38.914183+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMNB2P56NRT4HWSQ","created_at":"2026-07-05T11:37:38.914183+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMNB2P56","created_at":"2026-07-05T11:37:38.914183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02391","citing_title":"WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10556","citing_title":"EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02776","citing_title":"Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10556","citing_title":"EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06113","citing_title":"Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05615","citing_title":"LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05615","citing_title":"LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06113","citing_title":"Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16682","citing_title":"KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM","json":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM.json","graph_json":"https://pith.science/api/pith-number/RMNB2P56NRT4HWSQK335ZMSYKM/graph.json","events_json":"https://pith.science/api/pith-number/RMNB2P56NRT4HWSQK335ZMSYKM/events.json","paper":"https://pith.science/paper/RMNB2P56"},"agent_actions":{"view_html":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM","download_json":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM.json","view_paper":"https://pith.science/paper/RMNB2P56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11417&json=true","fetch_graph":"https://pith.science/api/pith-number/RMNB2P56NRT4HWSQK335ZMSYKM/graph.json","fetch_events":"https://pith.science/api/pith-number/RMNB2P56NRT4HWSQK335ZMSYKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM/action/storage_attestation","attest_author":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM/action/author_attestation","sign_citation":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM/action/citation_signature","submit_replication":"https://pith.science/pith/RMNB2P56NRT4HWSQK335ZMSYKM/action/replication_record"}},"created_at":"2026-07-05T11:37:38.914183+00:00","updated_at":"2026-07-05T11:37:38.914183+00:00"}