检索是不够的：为什么组织AI需要认知基础设施
Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
AI总结：
本文提出OIDA框架，通过类型化知识对象、知识重力引擎和问题原语，解决组织AI中检索系统缺乏认知结构的问题，并引入认知质量评分（EQS）进行评估。
摘要：
AI代理使用的组织知识通常缺乏认知结构：检索系统会呈现语义相关的内容，而不区分约束性决策与放弃的假设、有争议的主张与已解决的问题、已知事实与未解决的问题。我们认为，组织AI的上限不是检索保真度，而是认知保真度——即系统将承诺强度、矛盾状态和组织无知表示为可计算属性的能力。我们提出了OIDA，这是一个框架，将组织知识结构化为类型化的知识对象，这些对象带有认知类别、具有类别特定衰减的重要性分数以及带符号的矛盾边。知识重力引擎以确定性方式维护分数，并具有经过证明的收敛保证（充分条件：最大度数<7；经验上对度数为43的情况鲁棒）。OIDA引入了“问题”作为模型化的无知：一种具有反向衰减的原语，以越来越紧迫的方式揭示组织不知道什么——这是所有被调查系统中缺失的机制。我们描述了认知质量评分（EQS），一种包含五个组成部分的评估方法，并带有明确的循环性分析。在受控比较（n=10个响应对）中，OIDA的RAG条件（3,868个令牌）达到EQS 0.530，而全上下文基线（108,687个令牌）为0.848；28.1倍的令牌预算差异是主要的混淆因素。问题机制在统计上得到验证（Fisher p=0.0325，OR=21.0）。形式化属性已建立；在相等令牌预算下的决定性消融实验（E4）已预注册但尚未运行。
英文摘要：
Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones, or known facts from unresolved questions. We argue that the ceiling on organizational AI is not retrieval fidelity but \emph{epistemic} fidelity--the system's ability to represent commitment strength, contradiction status, and organizational ignorance as computable properties. We present OIDA, a framework that structures organizational knowledge as typed Knowledge Objects carrying epistemic class, importance scores with class-specific decay, and signed contradiction edges. The Knowledge Gravity Engine maintains scores deterministically with proved convergence guarantees (sufficient condition: max degree $< 7$; empirically robust to degree 43). OIDA introduces QUESTION-as-modeled-ignorance: a primitive with inverse decay that surfaces what an organization does \emph{not} know with increasing urgency--a mechanism absent from all surveyed systems. We describe the Epistemic Quality Score (EQS), a five-component evaluation methodology with explicit circularity analysis. In a controlled comparison ($n{=}10$ response pairs), OIDA's RAG condition (3,868 tokens) achieves EQS 0.530 vs.\ 0.848 for a full-context baseline (108,687 tokens); the $28.1\times$ token budget difference is the primary confound. The QUESTION mechanism is statistically validated (Fisher $p{=}0.0325$, OR$=21.0$). The formal properties are established; the decisive ablation at equal token budget (E4) is pre-registered and not yet run.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
