{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JEBUVC5PKUUY6WVBDRGY5G4GHW","short_pith_number":"pith:JEBUVC5P","schema_version":"1.0","canonical_sha256":"49034a8baf55298f5aa11c4d8e9b863d8e23f4be2ed6b48506df63e981aac679","source":{"kind":"arxiv","id":"2607.26571","version":1},"attestation_state":"computed","paper":{"title":"From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Elli Vartziotis, Francesca Dominici, George Dasoulas, Konstantinos Skianis, Michael Keckeisen, Rodopi Kosteli, Sotirios Kotsopoulos, Tina Vartziotis","submitted_at":"2026-07-29T07:50:55Z","abstract_excerpt":"The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems. However, direct measurement of inference energy often requires hardware telemetry, power instrumentation, or infrastructure-specific monitoring, limiting its applicability in comparative studies, early-stage system design, and sustainability reporting. This report presents an analytically structured, empirically calibrated, GPU-level methodology for estimating LLM inference energy on NVIDIA H100-class accelerators with"},"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":"2607.26571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T07:50:55Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"4beb3a45e52c0cdf905718c1f6cff41eb905f86ddf774951039108aa437b5e03","abstract_canon_sha256":"94697302ea723bd65041362bb565f9c945394500cadbd59fa3b1b770caf91298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49034a8baf55298f5aa11c4d8e9b863d8e23f4be2ed6b48506df63e981aac679","last_reissued_at":"2026-07-30T01:20:55.395511Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:55.395511Z"},"graph_snapshot":{"paper":{"title":"From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Elli Vartziotis, Francesca Dominici, George Dasoulas, Konstantinos Skianis, Michael Keckeisen, Rodopi Kosteli, Sotirios Kotsopoulos, Tina Vartziotis","submitted_at":"2026-07-29T07:50:55Z","abstract_excerpt":"The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems. However, direct measurement of inference energy often requires hardware telemetry, power instrumentation, or infrastructure-specific monitoring, limiting its applicability in comparative studies, early-stage system design, and sustainability reporting. This report presents an analytically structured, empirically calibrated, GPU-level methodology for estimating LLM inference energy on NVIDIA H100-class accelerators with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26571","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/2607.26571/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":"2607.26571","created_at":"2026-07-30T01:20:55.400866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26571v1","created_at":"2026-07-30T01:20:55.400866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26571","created_at":"2026-07-30T01:20:55.400866+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEBUVC5PKUUY","created_at":"2026-07-30T01:20:55.400866+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEBUVC5PKUUY6WVB","created_at":"2026-07-30T01:20:55.400866+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEBUVC5P","created_at":"2026-07-30T01:20:55.400866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW","json":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW.json","graph_json":"https://pith.science/api/pith-number/JEBUVC5PKUUY6WVBDRGY5G4GHW/graph.json","events_json":"https://pith.science/api/pith-number/JEBUVC5PKUUY6WVBDRGY5G4GHW/events.json","paper":"https://pith.science/paper/JEBUVC5P"},"agent_actions":{"view_html":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW","download_json":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW.json","view_paper":"https://pith.science/paper/JEBUVC5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26571&json=true","fetch_graph":"https://pith.science/api/pith-number/JEBUVC5PKUUY6WVBDRGY5G4GHW/graph.json","fetch_events":"https://pith.science/api/pith-number/JEBUVC5PKUUY6WVBDRGY5G4GHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW/action/storage_attestation","attest_author":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW/action/author_attestation","sign_citation":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW/action/citation_signature","submit_replication":"https://pith.science/pith/JEBUVC5PKUUY6WVBDRGY5G4GHW/action/replication_record"}},"created_at":"2026-07-30T01:20:55.400866+00:00","updated_at":"2026-07-30T01:20:55.400866+00:00"}