Mathematical reasoning systems should be consistent when the same concept is expressed in equivalent forms. This requires not only recognizing shared mathematical meaning but also identifying the representation changes and reconstructing a traceable route between forms. We study this problem through mathematical theorems, whose equivalent formulations preserve the same underlying result while differing substantially in representation. In this setting, theorem recognition is only the first step: a robust system must also identify the intervening transformations and recover their order. We introduce an evaluation of robust procedural mathematical reasoning with three components: theorem identification, transformation identification, and ordered reconstruction. Using validated theorem–representation pairs from an existing corpus, we build a procedural-robustness dataset with typed operations, reference procedures, and matched contrasts that distinguish valid reformulations from invalid ones. We first measure closed-book performance of four open-weight models to establish a baseline, then evaluate retrieval-augmented generation (RAG) as support mechanism for the same task. Models identify theorem identity more reliably than they recover the transformations and ordered routes connecting equivalent representations. RAG improves every stage, but procedural reconstruction remains the main bottleneck. The framework supports more consistent and traceable mathematical systems, with potential applications in mathematical search, tutoring, autoformalization, and scientific discovery.

Comments are widely used by users in collaborative documents every day. The documents’ comments enable collaborative editing and review dynamics, transforming each document into a context-sensitive communication channel. Understanding the role of comments in communication dynamics within documents is the first step towards automating their management. In this paper we propose the first ever taxonomy for different types of in-document comments based on analysis of a large scale dataset of public documents from the web. We envision that the next generation of intelligent collaborative document experiences allow interactive creation and consumption of content, there We also introduce the components necessary for developing novel tools that automate the handling of comments through natural language interaction with the documents. We identify the commands that users would use to respond to various types of comments. We train machine learning algorithms to recognize the different types of comments and assess their feasibility. We conclude by discussing some of the implications for the design of automatic document management tools.