{"paper":{"title":"Intelligence Delivery Network: Toward an Internet Architecture for the AI Age","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The Intelligence Delivery Network treats AI capabilities as deliverable network services positioned across cloud, edge, and local environments based on demand and resources.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Dan Zhao, Hanling Wang, Peiyuan Zong, Qing Li, Teng Gao, Xingchi Chen, Yong Jiang, Yue Yu, Yuhong Song, Zhuyun Qi","submitted_at":"2026-05-13T09:24:27Z","abstract_excerpt":"The rapid emergence of AI-powered applications is reshaping the role of the Internet. Users increasingly rely on the network to obtain intelligence services derived from large foundation models, rather than merely to reach remote endpoints or retrieve specific content. Today's dominant deployment paradigm for AI services remains cloud-centric, where user requests are transmitted to remote data centers for centralized inference. Although operationally convenient, this paradigm suffers from latency and jitter, heavy wide-area traffic, limited utilization of distributed heterogeneous compute reso"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose the Intelligence Delivery Network (IDN), an Internet architecture that treats AI capabilities as deliverable network services. The key idea is to position, select, reuse, and verify intelligence across cloud, regional, edge, and local environments according to demand locality, resource availability, and policy constraints.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That capability abstraction, compute resource integration, demand-driven deployment, service routing, state-aware caching, and trust management can jointly support distributed AI services without introducing prohibitive new overheads or security vulnerabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"IDN proposes treating AI intelligence as deliverable network services positioned dynamically across distributed compute environments to improve efficiency, latency, and privacy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Intelligence Delivery Network treats AI capabilities as deliverable network services positioned across cloud, edge, and local environments based on demand and resources.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"10d777b150bebfeadf938b04f0fa81165803f49e8621a74f69c2008f3a12648a"},"source":{"id":"2605.13235","kind":"arxiv","version":1},"verdict":{"id":"52c4b0e6-fe35-45b4-a376-e18903a14fd6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:28:10.249255Z","strongest_claim":"We propose the Intelligence Delivery Network (IDN), an Internet architecture that treats AI capabilities as deliverable network services. The key idea is to position, select, reuse, and verify intelligence across cloud, regional, edge, and local environments according to demand locality, resource availability, and policy constraints.","one_line_summary":"IDN proposes treating AI intelligence as deliverable network services positioned dynamically across distributed compute environments to improve efficiency, latency, and privacy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That capability abstraction, compute resource integration, demand-driven deployment, service routing, state-aware caching, and trust management can jointly support distributed AI services without introducing prohibitive new overheads or security vulnerabilities.","pith_extraction_headline":"The Intelligence Delivery Network treats AI capabilities as deliverable network services positioned across cloud, edge, and local environments based on demand and resources."},"references":{"count":48,"sample":[{"doi":"","year":2024,"title":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Tam- ing Throughput-Latency tradeoff in LLM inference with Sar","work_id":"0fc065d6-8f5a-4640-9254-5a82eb99e63e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"AMD. 2020. AMD SEV-SNP: Strengthening VM Isolation with Integrity Protec- tion and More. https://docs.amd.com/v/u/en-US/SEV-SNP-strengthening-vm- isolation-with-integrity-protection-and-more Accessed ","work_id":"5c5bc9cc-f43e-46b5-9c75-2f535671c038","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Sergei Arnautov, Bohdan Trach, Franz Gregor, Thomas Knauth, Andre Martin, Christian Priebe, Joshua Lind, Divya Muthukumaran, Dan O’keeffe, Mark L Stillwell, et al. 2016. SCONE: Secure linux containers","work_id":"4514a8bc-a0a9-47ab-9783-4a6f65ee3b02","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1974,"title":"Vinton Cerf and Robert Kahn. 1974. A protocol for packet network intercommu- nication.IEEE Transactions on communications22, 5 (1974), 637–648","work_id":"1d2fad1a-9935-4777-b6ee-8006099ee1a1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1988,"title":"David Clark. 1988. The design philosophy of the DARPA Internet protocols. In Symposium proceedings on Communications architectures and protocols. Associa- tion for Computing Machinery, Stanford, Unite","work_id":"1cc56fcb-f84f-4a82-a9b1-636c886bfa3e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"2b14108e25dc0968afca05dc856f063dd60ec774ed2a3f6cf69caca181a12d68","internal_anchors":4},"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"}