{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3RJNFW3LPUADTQZCTGKS24J3XJ","short_pith_number":"pith:3RJNFW3L","schema_version":"1.0","canonical_sha256":"dc52d2db6b7d0039c32299952d713bba7a927c84fa9675fb954474a0b476f57f","source":{"kind":"arxiv","id":"2608.06723","version":1},"attestation_state":"computed","paper":{"title":"Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Massoud Pedram, Mehdi Kamal, Mohammad Erfan Sadeghi, Saeid Shokoufa","submitted_at":"2026-08-07T02:37:02Z","abstract_excerpt":"The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design. In this work, we introduce Hybrid Modeling for Energy and Latency of LLMs (HYMELL), a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML). HYMELL models LLM execution through a three-level hierarchy: analytical estimation of primitive operations, ML predictio"},"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":"2608.06723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T02:37:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0bf60632fcdccc44ca5ec4bbef9eaeb59f20f8334c909dee911a005564124bb","abstract_canon_sha256":"98abd61cc3b772c06d06bcb8f826aafaa1ac3ff895d7a5cf983291459eb2299c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:49.521542Z","signature_b64":"//Fkqbbo9WEb/bJTOxpTfpFSj1AKNEWKjteopYF84MPu/O6F2rMLvpVmawhMTblJ+rHZM7x4ZMQj6BK0GR+sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc52d2db6b7d0039c32299952d713bba7a927c84fa9675fb954474a0b476f57f","last_reissued_at":"2026-08-10T01:11:49.519156Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:49.519156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Massoud Pedram, Mehdi Kamal, Mohammad Erfan Sadeghi, Saeid Shokoufa","submitted_at":"2026-08-07T02:37:02Z","abstract_excerpt":"The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design. In this work, we introduce Hybrid Modeling for Energy and Latency of LLMs (HYMELL), a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML). HYMELL models LLM execution through a three-level hierarchy: analytical estimation of primitive operations, ML predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06723","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/2608.06723/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":"2608.06723","created_at":"2026-08-10T01:11:49.520095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06723v1","created_at":"2026-08-10T01:11:49.520095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06723","created_at":"2026-08-10T01:11:49.520095+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RJNFW3LPUAD","created_at":"2026-08-10T01:11:49.520095+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RJNFW3LPUADTQZC","created_at":"2026-08-10T01:11:49.520095+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RJNFW3L","created_at":"2026-08-10T01:11:49.520095+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/3RJNFW3LPUADTQZCTGKS24J3XJ","json":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ.json","graph_json":"https://pith.science/api/pith-number/3RJNFW3LPUADTQZCTGKS24J3XJ/graph.json","events_json":"https://pith.science/api/pith-number/3RJNFW3LPUADTQZCTGKS24J3XJ/events.json","paper":"https://pith.science/paper/3RJNFW3L"},"agent_actions":{"view_html":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ","download_json":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ.json","view_paper":"https://pith.science/paper/3RJNFW3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06723&json=true","fetch_graph":"https://pith.science/api/pith-number/3RJNFW3LPUADTQZCTGKS24J3XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3RJNFW3LPUADTQZCTGKS24J3XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ/action/storage_attestation","attest_author":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ/action/author_attestation","sign_citation":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ/action/citation_signature","submit_replication":"https://pith.science/pith/3RJNFW3LPUADTQZCTGKS24J3XJ/action/replication_record"}},"created_at":"2026-08-10T01:11:49.520095+00:00","updated_at":"2026-08-10T01:11:49.520095+00:00"}