Lemma-style Math Reader

Instant cross-reference lookup and AI-completed proofs for dense math textbooks

Problem

When reading books like The Elements of Statistical Learning, the text constantly says things like 'see (3.41)' or 'by Theorem 2.3', forcing readers to scroll back through the whole book. Whenever a proof skips steps, readers screenshot it, ask ChatGPT, then manually paste notes back into the PDF—a broken workflow.

Solution

A desktop math reader that detects formulas, theorems, and lemmas in PDF/EPUB and turns them into clickable anchors. Clicking shows the referenced content in a popover. For skipped proof steps, it sends the context and formula to an AI to return a step-by-step derivation, saved as an inline annotation. All annotations live locally and export to Markdown.

Users

Graduate students, quants, and self-learners who read probability, statistics, and machine learning theory textbooks closely.

MVP

PDF only; detect and link equation/theorem numbers; click to show referenced content; call user's own API key to explain a selected formula in one step and save as annotation; store annotations in local SQLite and export to Markdown.

Revenue

One-time purchase of $19–29; free tier capped at 30 AI explanations per month; later sell a subscription to a 'textbook reference graph'.

Why now

LLMs can now reliably explain math derivations; what's missing is a lightweight tool that connects reading position, references, explanations, and notes. PDF parsing and formula anchoring are mature enough for a solo developer.