arXiv cs.AI· Yaxiao Liu (PwC China AI Center), Pengbo Liu (PwC China AI Center), Yiwen Liu (PwC China AI Center), Yihua Guan (PwC China AI Center), Jiaxing Song (Tsinghua University)·· 4 小时前AI 评分28
5W1H+Which：基于上下文有效语义索引与渐进式本体绑定的提出
5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding
AI 导读
Yaxiao Liu 在 arXiv 提出名为 5W1H+Which 的语义索引设计，将源内容提取与渐进式本体绑定分离：5W1H 问题组织可独立寻址的内容单元，Which 记录与版本化本体元素的链接、映射关系、适用范围与验证状态。该设计区分业务有效时间、系统知识时间与操作痕迹，未绑定内容仍可搜索，正式推理需显式前提检查。论文尚无实验结果，也未声称性能提升，仅为一份提出的索引与维护契约。
正文 · 原文
Abstract:Semantic indexing must preserve reusable source information without committing too early to one business schema, while providing checkable premises for reasoning. We propose 5W1H+Which, a design that separates source-grounded content extraction from progressive ontology binding. The 5W1H questions organize independently addressable content units; Which records links to versioned ontology elements, mapping relations, applicability scopes, and validation states. Time, location, system environment, and participant roles constrain when facts, bindings, and rules may be used. Unbound content remains searchable, whereas formal reasoning requires explicit premise checks. The design distinguishes business valid time, system knowledge time, and operational traces, and tracks dependencies for revalidation and incremental maintenance. Worked examples illustrate cloud migration and temporal policy validity. The resulting linked corpus can support downstream training and evaluation organized around benchmarks, positive and negative examples, trajectories, and costs. Trajectories preserve steps, evidence-backed checkpoints, recovery, and local-to-global failure impact; reusable skills remain downstream abstractions requiring cross-episode validation. We specify falsifiable hypotheses and capability-matched baselines to test cross-task evidence coverage, contextual misuse, and update cost under equal information and budgets. The contribution is a proposed indexing and maintenance contract, not a new universal ontology or post-training algorithm. No experiments have yet been conducted, and no performance improvement is claimed.
| Comments: | 30 pages, 6 figures, 7 tables. Expanded related work and temporal policy examples; added an indexed-corpus application for training and evaluation, including trajectory checkpoints, recovery, and partial-failure impact. Revised figures and abstract. Proposed method and evaluation design; no empirical results |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2609.35184 [cs.AI] |
| (or arXiv:2609.35184v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35184 arXiv-issued DOI via DataCite |
Submission history
From: Yaxiao Liu [view email]
[v1]
Mon, 28 Sep 2026 13:47:20 UTC (105 KB)
[v2]
Sun, 25 Oct 2026 06:07:04 UTC (192 KB)
来源：arXiv cs.AI · arxiv.org