DigClaw预测框架Rhizome在FutureX评测获三个Top席位
DigClaw用因果推理加概率校准构建预测基础设施，在公开评测中证明AI预测可系统化，超越模型本身。
DigClaw的预测框架Rhizome在FutureX实时预测榜单拿下第一名、第三名和第七名，且三个席位来自不同基础模型。这说明检索、推理、概率校准等能力可以沉淀为独立于模型权重的系统能力，基座可替换而预测资产持续积累。
正文摘录
July, DigClaw's prediction framework Rhizome v1 secured three spots — 1, 3, and 7 — on the FutureX evaluation platform. The three spots came from three different base models, including Kimi-K3, DeepSeek-V4-Pro, and others. DigClaw is the only participant that got the same framework to push all three into the Top 7. As foundation models improve, the system gains capability dividends; prediction trajectories, settlement feedback, calibration experience, and continuously evolving workflows keep accumulating inside the system. This is not an accidental contest result — it is the first external validation of DigClaw's answer to the question: "How should prediction actually be done?" LLMs learn correlation, not causation. They extract patterns from past corpora, but "learning from the past" and …