{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LNVX7VTQRK7A7STRTR5HMJT5NP","short_pith_number":"pith:LNVX7VTQ","schema_version":"1.0","canonical_sha256":"5b6b7fd6708abe0fca719c7a76267d6bf3190baf000430643f4f3f7ffe1cec09","source":{"kind":"arxiv","id":"2607.17175","version":1},"attestation_state":"computed","paper":{"title":"LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Mario Colosi, Reza Farahani, Schahram Dustdar, Zoha Azimi","submitted_at":"2026-07-19T10:21:30Z","abstract_excerpt":"Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user- and system-level quality of service (QoS) requirements. This paper introduces LMEdge, a QoS-aware orchestration service that dynamically makes these decisions across heterogeneous edge devices. We fo"},"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":"2607.17175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-19T10:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"95d08a4e063e2a5f238219bb35b9cab3ce729d77c2f1b2ae74672d696359d5b1","abstract_canon_sha256":"3606b2d7ddf77bfa9bc38cac08fb2b90d656bca2b4d34ae1bc1aa83aeb2bc946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:19.377707Z","signature_b64":"4fW+EX/ezPTXcVeGuXOYAZoyHTJxUG3kYJ0Vc14ArGqMVltF3/VGbXKIdJrOba3fRhlvs8ySWmtORmJUhWkBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b6b7fd6708abe0fca719c7a76267d6bf3190baf000430643f4f3f7ffe1cec09","last_reissued_at":"2026-07-21T01:21:19.376776Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:19.376776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Mario Colosi, Reza Farahani, Schahram Dustdar, Zoha Azimi","submitted_at":"2026-07-19T10:21:30Z","abstract_excerpt":"Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user- and system-level quality of service (QoS) requirements. This paper introduces LMEdge, a QoS-aware orchestration service that dynamically makes these decisions across heterogeneous edge devices. We fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17175","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/2607.17175/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":"2607.17175","created_at":"2026-07-21T01:21:19.377223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17175v1","created_at":"2026-07-21T01:21:19.377223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17175","created_at":"2026-07-21T01:21:19.377223+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNVX7VTQRK7A","created_at":"2026-07-21T01:21:19.377223+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNVX7VTQRK7A7STR","created_at":"2026-07-21T01:21:19.377223+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNVX7VTQ","created_at":"2026-07-21T01:21:19.377223+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/LNVX7VTQRK7A7STRTR5HMJT5NP","json":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP.json","graph_json":"https://pith.science/api/pith-number/LNVX7VTQRK7A7STRTR5HMJT5NP/graph.json","events_json":"https://pith.science/api/pith-number/LNVX7VTQRK7A7STRTR5HMJT5NP/events.json","paper":"https://pith.science/paper/LNVX7VTQ"},"agent_actions":{"view_html":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP","download_json":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP.json","view_paper":"https://pith.science/paper/LNVX7VTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17175&json=true","fetch_graph":"https://pith.science/api/pith-number/LNVX7VTQRK7A7STRTR5HMJT5NP/graph.json","fetch_events":"https://pith.science/api/pith-number/LNVX7VTQRK7A7STRTR5HMJT5NP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP/action/storage_attestation","attest_author":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP/action/author_attestation","sign_citation":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP/action/citation_signature","submit_replication":"https://pith.science/pith/LNVX7VTQRK7A7STRTR5HMJT5NP/action/replication_record"}},"created_at":"2026-07-21T01:21:19.377223+00:00","updated_at":"2026-07-21T01:21:19.377223+00:00"}