{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X7IMXQ4KGYTYXY6ZCHTISQV3F6","short_pith_number":"pith:X7IMXQ4K","schema_version":"1.0","canonical_sha256":"bfd0cbc38a36278be3d911e68942bb2fba7b5f66705ec09cd3c8bd0102e6a10a","source":{"kind":"arxiv","id":"2608.05926","version":1},"attestation_state":"computed","paper":{"title":"BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NI","authors_text":"Guanqiao Qu, Kin K. Leung, Qian Chen, Shuo Chen, Xianhao Chen","submitted_at":"2026-08-06T11:57:36Z","abstract_excerpt":"Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: Autoregressive decoding (AD) generates output tokens sequentially, resulting in long latency; Speculative decoding (SD) accelerates inference by using a small language model (SLM) to generate multiple draft tokens for LLM verification, but incurs extra memory costs. Due to this latency-memory tradeoff, neither approach alone can efficiently serve users with heterogeneous demands under limited edge computing resources."},"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":"2608.05926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-08-06T11:57:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4977f9a7c55c0ae0092c0ec647b94218308e1ea5e52e58dfa61b4f403d2dae9d","abstract_canon_sha256":"f0b996690531e24da5eab533333730957ceb935f30381a155c753e23ec97ace9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:53:20.695574Z","signature_b64":"HYvNd/m+7bQrUqNAon0mDiTQ/HcUqzs+Q4ZmZvqcwyUga07QuMga2Wq5SIFhcjf7IInhm/mct23sqDG5p57dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfd0cbc38a36278be3d911e68942bb2fba7b5f66705ec09cd3c8bd0102e6a10a","last_reissued_at":"2026-08-07T00:53:20.693977Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:53:20.693977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NI","authors_text":"Guanqiao Qu, Kin K. Leung, Qian Chen, Shuo Chen, Xianhao Chen","submitted_at":"2026-08-06T11:57:36Z","abstract_excerpt":"Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: Autoregressive decoding (AD) generates output tokens sequentially, resulting in long latency; Speculative decoding (SD) accelerates inference by using a small language model (SLM) to generate multiple draft tokens for LLM verification, but incurs extra memory costs. Due to this latency-memory tradeoff, neither approach alone can efficiently serve users with heterogeneous demands under limited edge computing resources."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05926","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/2608.05926/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":"2608.05926","created_at":"2026-08-07T00:53:20.695528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05926v1","created_at":"2026-08-07T00:53:20.695528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05926","created_at":"2026-08-07T00:53:20.695528+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7IMXQ4KGYTY","created_at":"2026-08-07T00:53:20.695528+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7IMXQ4KGYTYXY6Z","created_at":"2026-08-07T00:53:20.695528+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7IMXQ4K","created_at":"2026-08-07T00:53:20.695528+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/X7IMXQ4KGYTYXY6ZCHTISQV3F6","json":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6.json","graph_json":"https://pith.science/api/pith-number/X7IMXQ4KGYTYXY6ZCHTISQV3F6/graph.json","events_json":"https://pith.science/api/pith-number/X7IMXQ4KGYTYXY6ZCHTISQV3F6/events.json","paper":"https://pith.science/paper/X7IMXQ4K"},"agent_actions":{"view_html":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6","download_json":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6.json","view_paper":"https://pith.science/paper/X7IMXQ4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05926&json=true","fetch_graph":"https://pith.science/api/pith-number/X7IMXQ4KGYTYXY6ZCHTISQV3F6/graph.json","fetch_events":"https://pith.science/api/pith-number/X7IMXQ4KGYTYXY6ZCHTISQV3F6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6/action/storage_attestation","attest_author":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6/action/author_attestation","sign_citation":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6/action/citation_signature","submit_replication":"https://pith.science/pith/X7IMXQ4KGYTYXY6ZCHTISQV3F6/action/replication_record"}},"created_at":"2026-08-07T00:53:20.695528+00:00","updated_at":"2026-08-07T00:53:20.695528+00:00"}