arXiv：cs.AI· Wenbin Mao, Pei Zou·· 10 小时前
Pre-Registered Genesis Accounting：物理发现运行时中首次通过审计的算子创世事件
Pre-Registered Genesis Accounting for Recursive Self-Improvement: First Audited Operator-Genesis Events in a Physics-Discovery Runtime
AI 导读
研究者提出 M1/M2 双层记账框架，用于区分机器复用设计者机制与自主创制机制，并报告了首批通过审计的 M2 创世事件。
正文
Abstract:Claims of recursive self-improvement are easy to make and hard to falsify: did improvement come from re-using designer-provided mechanisms, or from mechanisms the system authored itself? We introduce a pre-registered, two-tier accounting: M1 counts machine-generated content instances within a designer-provided vocabulary, while M2 counts machine-authored mechanism types (new operators registered into the runtime's own vocabulary, with a held-out-validation certificate). We report the first audited M2 genesis events. In the primary event, depth-limited compositional search over elementary operators, judged by held-out R^2 on real NIST hydrogen Balmer measurements, produced the operator sq(inv(n)) = 1/n^2 -- the Rydberg-level form -- which no standard-library transform could express (held-out R^2: -0.546 best standard transform vs. 1.0000000 composed). A protocol flaw (independent variable built by inverting the very law under test) was caught in audit and repaired via an independent-label protocol; extrapolation to unseen levels (n=8,9 trained on n<=7) attains relative error ~10^-6, four to six orders beyond the best standard operator. A second event independently recovered sqrt(inv(a)) -- Kepler's velocity law -- from JPL ephemeris vectors. Also incorporated: an audited compounding channel (first domain-level measurement: 1.109x accuracy ratio on a real held-out domain) and blind, decurated genesis exams whose honest tally is zero. The Kepler event passes line audit; the hydrogen gap reproduces on He II; the certificate is threshold-stable. Against eleven prior systems, the contribution is the measurement and governance of machine-authored mechanisms, not the search algorithm or rediscovered physics. Limitations: exams were curated by agents who knew the textbook answer, triggers manual, grammar observer-injected; both events demonstrate capability to author, not yet autonomous genesis.
| Comments: | 7 pages, 1 figure |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14843 [cs.AI] |
| (or arXiv:2610.14843v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14843 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenbin Mao [view email]
[v1]
Sat, 10 Oct 2026 11:57:42 UTC (13 KB)
来源：arXiv：cs.AI · arxiv.org