Newest papers

Knowledge as Code

Martin Monperrus · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27693 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

何千年もの間、知識は言語によって受け継がれ、大規模な言語モデルはまだ言語を中心に置いています。しかし、これらのモデルに構築されたコーディングエージェントは主にコードを書きます。この論文は、知識コードがどのような種類であり、どのように得られるかを問うエピステモロジーへの貢献です。我々は、プログラミング言語や機械で読み取れるデータフォーマットで書かれた知識として知識をコードと定義し、その有効性はそれを実行することによって検証することができます。我々は知識メディアの13のエピステマ特性を定義し、コードがそれらすべてを持っている最初のメディアであることを示します。我々は、コードがコードに入る2つの方法、コード

Machine translation (Meta M2M100); the English original follows.

Abstract

For millennia, knowledge has been carried by language, and large language models still put language at the center. Yet the coding agents built on these models mostly write code. This paper is a contribution to epistemology, which asks what kind of knowledge code is and how it is obtained. We define knowledge as code as knowledge written in a programming language or in a machine-parsable data format, whose validity can be checked by executing it. We define thirteen epistemic properties of knowledge media and show that code is the first medium to have all of them. We distinguish two ways in which knowledge enters code, encoding and learning by execution, where code is both the experiment and the record of its result. Agents make learning by execution observable, since their trajectories record every probe, observation and line of code they keep. Code is thus not only a tool of knowledge work but a knowledge medium in its own right, the first that can check what it holds.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Code (set theory), Programming language, Coding (social sciences), Knowledge-based systems, Knowledge extraction

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange