---
title: "Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05753v1"
permalink: "https://feed.astralor.com/items/itm_5c181e4edf3b5a19241f31ae"
published: "2026-11-03T23:50:38.000Z"
score: 56
channel: "ai"
tags: ["AI Agent","RAG","Toward","Compositional Knowledge Architecture","Shared Organizational Cortex","Organizations","Existing","Signals"]
---

# Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex

## At a glance

Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circums…

## Key points

- Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circums…
- Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation.
- We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence chang…

## Full text

Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_5c181e4edf3b5a19241f31ae