用可验证的推理链构建科学百科，让知识有来源、可追溯。
Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base
- 从基础原理出发生成三百万个问题，构建可验证的长链条推理库。
- 通过多模型交叉验证，保留仅有真实结论的推理路径，准确率显著提升。
- 适合需要深度理解与跨领域知识整合的研究者和教育者使用。
多数科学材料压缩了推理过程，只呈现结论而省略推导链条，导致难以验证且阻碍跨领域关联。本文提出可扩展框架，解压科学推理，构建可验证的长链思维（LCoT）知识库，并投影为新兴百科全书SciencePedia。其流程采用目标驱动的还原策略：由苏格拉底式代理在约200门课程引导下生成约300万条基于第一性原理的问题。为保证高保真度，多个独立求解模型生成LCoT，经提示净化与多模型答案共识严格筛选，仅保留具备可验证终点的条目。该验证语料驱动头脑风暴搜索引擎，实现逆向知识搜索——检索出多样化的第一性原理推导，最终汇聚到目标概念。此引擎供给柏拉图合成器，将已验证的推理链转化为连贯文章。初始SciencePedia包含约20万条细粒度条目，覆盖数学、物理、化学、生物、工程与计算。在六大学科评估中，柏拉图合成的文章（基于检索到的LCoT）在知识点密度上远超无检索基线，且事实错误率显著更低（由外部大模型评估）。基于此可验证的LCoT知识库，该以推理为中心的方法实现了大规模可信、跨领域的科学知识融合，奠定了持续扩展百科全书的基础。
原文摘要 · Abstract (English)
Most scientific materials compress reasoning, presenting conclusions while omitting the derivational chains that justify them. This compression hinders verification by lacking explicit, step-wise justifications and inhibits cross-domain links by collapsing the very pathways that establish the logical and causal connections between concepts. We introduce a scalable framework that decompresses scientific reasoning, constructing a verifiable Long Chain-of-Thought (LCoT) knowledge base and projecting it into an emergent encyclopedia, SciencePedia. Our pipeline operationalizes an endpoint-driven, reductionist strategy: a Socratic agent, guided by a curriculum of around 200 courses, generates approximately 3 million first-principles questions. To ensure high fidelity, multiple independent solver models generate LCoTs, which are then rigorously filtered by prompt sanitization and cross-model answer consensus, retaining only those with verifiable endpoints. This verified corpus powers the Brainstorm Search Engine, which performs inverse knowledge search -- retrieving diverse, first-principles derivations that culminate in a target concept. This engine, in turn, feeds the Plato synthesizer, which narrates these verified chains into coherent articles. The initial SciencePedia comprises approximately 200,000 fine-grained entries spanning mathematics, physics, chemistry, biology, engineering, and computation. In evaluations across six disciplines, Plato-synthesized articles (conditioned on retrieved LCoTs) exhibit substantially higher knowledge-point density and significantly lower factual error rates than an equally-prompted baseline without retrieval (as judged by an external LLM). Built on this verifiable LCoT knowledge base, this reasoning-centric approach enables trustworthy, cross-domain scientific synthesis at scale and establishes the foundation for an ever-expanding encyclopedia.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。