arXiv cs.AI· Andrew Miracle, Phyl Georgiou, Christine Okoth, Ese Monday·· 12 小时前AI 评分31
面向共享组织皮层的组合式知识架构：Signals、Domains、Claims 与 Dimensions 四层设计
Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex
AI 导读
研究者提出 Signals、Domains、Claims、Dimensions 四层知识架构，让组织中的解读连同其依据与效力状态一起持久保存，并由真值维护网络随证据变化修订。
正文 · 原文
Abstract: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.
| Comments: | 25 pages, 10 figures, 10 tables. Evaluation and sources in this https URL (tag registered-plan) |
| Subjects: | Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.05753 [cs.AI] |
| (or arXiv:2611.05753v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05753 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andrew Miracle Mr [view email]
[v1]
Tue, 3 Nov 2026 23:50:38 UTC (317 KB)
来源：arXiv cs.AI · arxiv.org