{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6S7AAFKHFQLAQ5ISGB235IOCLT","short_pith_number":"pith:6S7AAFKH","schema_version":"1.0","canonical_sha256":"f4be0015472c160875123075bea1c25cf609da6f5f6f2c5edda902f70126025e","source":{"kind":"arxiv","id":"2508.11291","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Nan Xue, Rui Bao, Yaping Sun, Zhiyong Chen","submitted_at":"2025-08-15T07:55:05Z","abstract_excerpt":"The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between inference quality and end-to-end latency. A fundamental mismatch exists between task complexity and resource allocation: offloading simple queries invites prohibitive latency, while on-device models lack the capacity for demanding computations. To address this challenge, we propose a dynamic, quality-latency aware routing framework that orchestrates inference b"},"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":"2508.11291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-08-15T07:55:05Z","cross_cats_sorted":["cs.AI","cs.LG","math.IT"],"title_canon_sha256":"5e87a2b0b16a6adbbfe4404c3c5cac3dca3a81d4781bb3ff92aa4df4c274d72c","abstract_canon_sha256":"9cde3efe31a34177c7bf26f13f602276098307972e8b0774a21bc25b5946d021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:22.155507Z","signature_b64":"p48h3ZR0JneL2+r+BwgMfmYyh5A/ULLiz+yZ5rcrtfpR5wTK6e/ltB5l2KUc7uRzuhyYWecza4MDh0Blpsr+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4be0015472c160875123075bea1c25cf609da6f5f6f2c5edda902f70126025e","last_reissued_at":"2026-07-05T11:54:22.155041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:22.155041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Nan Xue, Rui Bao, Yaping Sun, Zhiyong Chen","submitted_at":"2025-08-15T07:55:05Z","abstract_excerpt":"The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between inference quality and end-to-end latency. A fundamental mismatch exists between task complexity and resource allocation: offloading simple queries invites prohibitive latency, while on-device models lack the capacity for demanding computations. To address this challenge, we propose a dynamic, quality-latency aware routing framework that orchestrates inference b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11291","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/2508.11291/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":"2508.11291","created_at":"2026-07-05T11:54:22.155096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11291v1","created_at":"2026-07-05T11:54:22.155096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11291","created_at":"2026-07-05T11:54:22.155096+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S7AAFKHFQLA","created_at":"2026-07-05T11:54:22.155096+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S7AAFKHFQLAQ5IS","created_at":"2026-07-05T11:54:22.155096+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S7AAFKH","created_at":"2026-07-05T11:54:22.155096+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/6S7AAFKHFQLAQ5ISGB235IOCLT","json":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT.json","graph_json":"https://pith.science/api/pith-number/6S7AAFKHFQLAQ5ISGB235IOCLT/graph.json","events_json":"https://pith.science/api/pith-number/6S7AAFKHFQLAQ5ISGB235IOCLT/events.json","paper":"https://pith.science/paper/6S7AAFKH"},"agent_actions":{"view_html":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT","download_json":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT.json","view_paper":"https://pith.science/paper/6S7AAFKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11291&json=true","fetch_graph":"https://pith.science/api/pith-number/6S7AAFKHFQLAQ5ISGB235IOCLT/graph.json","fetch_events":"https://pith.science/api/pith-number/6S7AAFKHFQLAQ5ISGB235IOCLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT/action/storage_attestation","attest_author":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT/action/author_attestation","sign_citation":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT/action/citation_signature","submit_replication":"https://pith.science/pith/6S7AAFKHFQLAQ5ISGB235IOCLT/action/replication_record"}},"created_at":"2026-07-05T11:54:22.155096+00:00","updated_at":"2026-07-05T11:54:22.155096+00:00"}