让AI推理结果可验证、可审计，确保每一步计算都公开可信。
EigenAI: Deterministic Inference, Verifiable Results
- 用确定性模型+加密日志，实现推理过程可复现。
- 通过受信任环境重算，1个诚实副本即可发现欺诈。
- 适合需要高可靠性的金融、科研等场景使用。
EigenAI 是基于 EigenLayer 重质押生态构建的可验证 AI 平台。它将确定性大语言模型（LLM）推理引擎与密码经济保障的乐观重执行协议结合，使每次推理结果均可公开审计、复现，必要时可经济强制执行。未被信任的运营商在固定 GPU 架构上运行推理，签名并加密请求与响应，将加密日志发布至 EigenDA。在挑战窗口内，任何观察者可通过 EigenVerify 请求重执行；结果在受信任执行环境（TEE）中以阈值释放的密钥下确定性重算，实现私有数据下的公开挑战。由于推理本身是位精确的，验证仅需字节级相等检查，一个诚实副本即足以检测欺诈。该架构支持主权智能体——如预测市场裁判、交易机器人和科学助手——在保持前沿性能的同时，继承以太坊验证者池的安全性。
原文摘要 · Abstract (English)
EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem. At a high level, it combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol so that every inference result can be publicly audited, reproduced, and, if necessary, economically enforced. An untrusted operator runs inference on a fixed GPU architecture, signs and encrypts the request and response, and publishes the encrypted log to EigenDA. During a challenge window, any watcher may request re-execution through EigenVerify; the result is then deterministically recomputed inside a trusted execution environment (TEE) with a threshold-released decryption key, allowing a public challenge with private data. Because inference itself is bit-exact, verification reduces to a byte-equality check, and a single honest replica suffices to detect fraud. We show how this architecture yields sovereign agents -- prediction-market judges, trading bots, and scientific assistants -- that enjoy state-of-the-art performance while inheriting security from Ethereum's validator base.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。