Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole program -- primitives, control flow, string I/O -- to one fused tensor-op graph over a frozen embedding substrate. Rotation binding, unbind, bundle, polynomial Kleene three-valued logic, and tail-recursive loops all lower to tensor operations; the Kleene connectives are Lagrange-interpolated polynomials exact on the {-1, 0, +1} truth grid. Validation is one fact tested two ways. (1) The same program runs on four frozen embeddings spanning two modalities -- three text encoders (nomic-embed-text, all-minilm, mxbai-embed-large) and one protein language model (ESM-2) -- and decodes bundles at 100% accuracy through width k=8 on every substrate, where the textbook Hadamard product has already collapsed (2.5% on mxbai-embed-large, 7.5% on all-minilm). (2) PyTorch autograd flows through the actually compiled graph: a fuzzy-rule classifier written in .su trains from random init (18.7 +/- 9.5%; chance = 20%, five classes) to 100.0 +/- 0.0% (three seeds) by backpropagating through the emitted graph, the symbolic source unmodified. A weighted variant additionally trains a scalar cosine gain and writes it back into the .su source as a numeric literal; recompiling reproduces the trained behaviour to ~2e-7 per logit, so the trained model is itself legible, recompilable code. The same artifact is therefore both a logic program and a trainable neural network.

翻译：摘要：Sutra是一种带类型的纯函数式编程语言，其编译后的前向传播过程是一个PyTorch神经网络。编译器将整个程序（包括原语、控制流、字符串I/O）通过β规约归约为一个在冻结嵌入基座上的融合张量操作图。旋转变换、解绑、捆绑、多项式Kleene三值逻辑以及尾递归循环均被降级为张量操作；其中Kleene联结词通过拉格朗日插值多项式精确适配{-1,0,+1}真值网格。验证采用同一事实的两种测试方式：(1) 同一程序在横跨两种模态的四种冻结嵌入上运行——三个文本编码器（nomic-embed-text、all-minilm、mxbai-embed-large）和一个蛋白质语言模型（ESM-2）——并在宽度k=8的所有基座上以100%准确率解码捆绑结果，而教科书级哈达玛积已在mxbai-embed-large（2.5%）和all-minilm（7.5%）上失效；(2) PyTorch自动微分通过实际编译的计算图流动：一个用.su编写的模糊规则分类器从随机初始化（18.7±9.5%；随机概率20%，五分类）通过反向传播生成的计算图训练至100.0±0.0%（三个随机种子），符号源代码保持不变。加权变体额外训练标量余弦增益，并将其作为数值常量写回.su源文件；重新编译后训练行为复现精度达每个logit约2e-7，因此训练后的模型本身就是可读、可重编译的代码。同一制品既是一个逻辑程序，又是一个可训练的神经网络。