用区块链记录学习过程，让AI决策可审计可验证。
MathLedger: A Verifiable Learning Substrate with Ledger-Attested Feedback
- 用形式化验证驱动学习更新，替代传统损失函数。
- 在控制环境下验证了测量与治理机制的有效性。
- 适合需要高可信度的AI系统，如医疗、金融领域。
当前AI系统虽表现卓越，但缺乏透明性与可验证性，难以用于安全关键场景。本文提出MathLedger，一种将形式化验证、密码学证明与学习动态融合的可验证机器认知基底。系统实现反射式形式学习（RFL），其更新由验证器结果驱动，而非统计损失。第一阶段实验在受控条件下验证了测量与治理基底：CAL-EXP-3验证了Δp计算与方差追踪的准确性；独立压力测试表明，在越界情况下系统能正确触发‘故障闭合’治理机制。未宣称收敛或能力提升。贡献为基础设施：一个可审计的链上学习原型系统。
原文摘要 · Abstract (English)
Contemporary AI systems achieve extraordinary performance yet remain opaque and non-verifiable, creating a crisis of trust for safety-critical deployment. We introduce MathLedger, a substrate for verifiable machine cognition that integrates formal verification, cryptographic attestation, and learning dynamics into a single epistemic loop. The system implements Reflexive Formal Learning (RFL), a symbolic analogue of gradient descent where updates are driven by verifier outcomes rather than statistical loss. Phase I experiments validate the measurement and governance substrate under controlled conditions. CAL-EXP-3 validates measurement infrastructure (Delta p computation, variance tracking); separate stress tests confirm fail-closed governance triggers correctly under out-of-bounds conditions. No convergence or capability claims are made. The contribution is infrastructural: a working prototype of ledger-attested learning that enables auditability at scale. Keywords: verifiable learning, formal verification, cryptographic attestation, reflexive feedback, fail-closed governance
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。