{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JPE36RB4JWWKKSJML5SKC6GANX","short_pith_number":"pith:JPE36RB4","schema_version":"1.0","canonical_sha256":"4bc9bf443c4daca5492c5f64a178c06ddc67bdeae70e93f63b6ab474f5e786f9","source":{"kind":"arxiv","id":"2608.01126","version":1},"attestation_state":"computed","paper":{"title":"Spatial Prefix Caching for Wireless Edge LLM Inference: A Stochastic-Geometry and Queueing Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Le Yang, Zhouyong Liu","submitted_at":"2026-08-02T09:51:15Z","abstract_excerpt":"Prefix caching reuses the key--value (KV) states of shared prompt prefixes and can substantially reduce the time to first token (TTFT) of large language model (LLM) inference. In a wireless edge network, however, prefix states are distributed across geographically separated GPU nodes. A nearby node offers a short radio path but may provide little reuse, whereas a more distant node may cache a longer matching prefix but incur additional communication and queueing delay. Moreover, persistent prefixes and active-request KV states compete for the same GPU memory, so aggressive caching can reduce i"},"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":"2608.01126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2026-08-02T09:51:15Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"341c30851dd0c0af5c75aaabe32869e31cac3403883e1f3753984d499deaee44","abstract_canon_sha256":"2776300d7a98ec4a2dbf2ac8d02d6250a3ce871723a79886202edf977233488e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:55.339505Z","signature_b64":"dKKfc4vao08rHXSz17b6yMmqMikWL4SF1VwN6DFFLqJzkIz8xMXj2Bp9Aa/4HXpeOB+a8YLT6vvSmENbt5XqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc9bf443c4daca5492c5f64a178c06ddc67bdeae70e93f63b6ab474f5e786f9","last_reissued_at":"2026-08-04T01:56:55.337866Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:55.337866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Prefix Caching for Wireless Edge LLM Inference: A Stochastic-Geometry and Queueing Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Le Yang, Zhouyong Liu","submitted_at":"2026-08-02T09:51:15Z","abstract_excerpt":"Prefix caching reuses the key--value (KV) states of shared prompt prefixes and can substantially reduce the time to first token (TTFT) of large language model (LLM) inference. In a wireless edge network, however, prefix states are distributed across geographically separated GPU nodes. A nearby node offers a short radio path but may provide little reuse, whereas a more distant node may cache a longer matching prefix but incur additional communication and queueing delay. Moreover, persistent prefixes and active-request KV states compete for the same GPU memory, so aggressive caching can reduce i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01126","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/2608.01126/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":"2608.01126","created_at":"2026-08-04T01:56:55.339160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01126v1","created_at":"2026-08-04T01:56:55.339160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01126","created_at":"2026-08-04T01:56:55.339160+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPE36RB4JWWK","created_at":"2026-08-04T01:56:55.339160+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPE36RB4JWWKKSJM","created_at":"2026-08-04T01:56:55.339160+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPE36RB4","created_at":"2026-08-04T01:56:55.339160+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/JPE36RB4JWWKKSJML5SKC6GANX","json":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX.json","graph_json":"https://pith.science/api/pith-number/JPE36RB4JWWKKSJML5SKC6GANX/graph.json","events_json":"https://pith.science/api/pith-number/JPE36RB4JWWKKSJML5SKC6GANX/events.json","paper":"https://pith.science/paper/JPE36RB4"},"agent_actions":{"view_html":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX","download_json":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX.json","view_paper":"https://pith.science/paper/JPE36RB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01126&json=true","fetch_graph":"https://pith.science/api/pith-number/JPE36RB4JWWKKSJML5SKC6GANX/graph.json","fetch_events":"https://pith.science/api/pith-number/JPE36RB4JWWKKSJML5SKC6GANX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX/action/storage_attestation","attest_author":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX/action/author_attestation","sign_citation":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX/action/citation_signature","submit_replication":"https://pith.science/pith/JPE36RB4JWWKKSJML5SKC6GANX/action/replication_record"}},"created_at":"2026-08-04T01:56:55.339160+00:00","updated_at":"2026-08-04T01:56:55.339160+00:00"}