Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915736575803392 |
|---|---|
| author | Li, Yu Huang, Yuan Wang, Tao Fan, Caiyu Cai, Xiansheng Hu, Sihan Liu, Xinzijian Shi, Cheng Xu, Mingjun Wang, Zhen Wang, Yan Jin, Xiangqi Zhang, Tianhan Zhang, Linfeng Wang, Lei Deng, Youjin Zhang, Pan Sun, Weijie Li, Xinyu E, Weinan Zhang, Linfeng Yao, Zhiyuan Chen, Kun |
| author_facet | Li, Yu Huang, Yuan Wang, Tao Fan, Caiyu Cai, Xiansheng Hu, Sihan Liu, Xinzijian Shi, Cheng Xu, Mingjun Wang, Zhen Wang, Yan Jin, Xiangqi Zhang, Tianhan Zhang, Linfeng Wang, Lei Deng, Youjin Zhang, Pan Sun, Weijie Li, Xinyu E, Weinan Zhang, Linfeng Yao, Zhiyuan Chen, Kun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26854 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base Li, Yu Huang, Yuan Wang, Tao Fan, Caiyu Cai, Xiansheng Hu, Sihan Liu, Xinzijian Shi, Cheng Xu, Mingjun Wang, Zhen Wang, Yan Jin, Xiangqi Zhang, Tianhan Zhang, Linfeng Wang, Lei Deng, Youjin Zhang, Pan Sun, Weijie Li, Xinyu E, Weinan Zhang, Linfeng Yao, Zhiyuan Chen, Kun Artificial Intelligence Machine Learning 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. |
| title | Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.26854 |