{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2K4MTNODVG3E6QUW6RD3ROWI5","short_pith_number":"pith:O2K4MTNO","schema_version":"1.0","canonical_sha256":"7695c64dae1d4db27a14b7a23dc5d64746b14205b93c5d586e673601a59b9d36","source":{"kind":"arxiv","id":"2607.13093","version":1},"attestation_state":"computed","paper":{"title":"Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Li, Jiexiong Liu, Yi Li","submitted_at":"2026-07-14T01:17:17Z","abstract_excerpt":"On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model h"},"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":"2607.13093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-14T01:17:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9dc6f258e4869c69d544bb393cf07bd82a2ae7e1d6e30e6382f008f56f3bfab2","abstract_canon_sha256":"8896c99115e4c15289bc76e0586b6a3072feb84a140c9092474465dfb4bed9c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:21:55.363678Z","signature_b64":"pWO4ap2bbGIrGYjwqeCdTCxlQEzdsjA/CKYFpMbDxaIxnfvZeto4TGTi59627dMiSxy2KN4b0EyLObDL6mC3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7695c64dae1d4db27a14b7a23dc5d64746b14205b93c5d586e673601a59b9d36","last_reissued_at":"2026-07-16T00:21:55.362840Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:21:55.362840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Li, Jiexiong Liu, Yi Li","submitted_at":"2026-07-14T01:17:17Z","abstract_excerpt":"On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13093","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/2607.13093/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":"2607.13093","created_at":"2026-07-16T00:21:55.363263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13093v1","created_at":"2026-07-16T00:21:55.363263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13093","created_at":"2026-07-16T00:21:55.363263+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2K4MTNODVG3","created_at":"2026-07-16T00:21:55.363263+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2K4MTNODVG3E6QU","created_at":"2026-07-16T00:21:55.363263+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2K4MTNO","created_at":"2026-07-16T00:21:55.363263+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/O2K4MTNODVG3E6QUW6RD3ROWI5","json":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5.json","graph_json":"https://pith.science/api/pith-number/O2K4MTNODVG3E6QUW6RD3ROWI5/graph.json","events_json":"https://pith.science/api/pith-number/O2K4MTNODVG3E6QUW6RD3ROWI5/events.json","paper":"https://pith.science/paper/O2K4MTNO"},"agent_actions":{"view_html":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5","download_json":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5.json","view_paper":"https://pith.science/paper/O2K4MTNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13093&json=true","fetch_graph":"https://pith.science/api/pith-number/O2K4MTNODVG3E6QUW6RD3ROWI5/graph.json","fetch_events":"https://pith.science/api/pith-number/O2K4MTNODVG3E6QUW6RD3ROWI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5/action/storage_attestation","attest_author":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5/action/author_attestation","sign_citation":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5/action/citation_signature","submit_replication":"https://pith.science/pith/O2K4MTNODVG3E6QUW6RD3ROWI5/action/replication_record"}},"created_at":"2026-07-16T00:21:55.363263+00:00","updated_at":"2026-07-16T00:21:55.363263+00:00"}