Scaling Accessible Mathematics on arXiv: HTML Conversion and MathML 4

• URL: http://arxiv.org/abs/2605.16562v1
• Date: Fri, 15 May 2026 19:04:45 GMT
• Title: Scaling Accessible Mathematics on arXiv: HTML Conversion and MathML 4
• Abstract summary: We report on the ongoing development of arXiv's HTML Papers offering, available on every new La submission since its initial release in 2023.<n>The main highlights from 2025 and early 2026 are: (i) community-driven improvements to HTML fidelity and service health, with roughly half of 6,000 user reports resolved.<n>An in-progress Rust port of HTMLML, reducing compute costs and enabling faster previews on submission.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: We report on the ongoing development of arXiv's HTML Papers offering, available on every new TeX/LaTeX submission since its initial release in 2023. The main highlights from 2025 and early 2026 are: (i) community-driven improvements to HTML fidelity and service health, with roughly half of 6,000 user reports resolved; (ii) corpus-scale conversion work aimed at 90% error-free HTML (currently 75%); (iii) initial MathML 4 Intent annotations for accessible speech output; (iv) an in-progress Rust port of LaTeXML, reducing compute costs and enabling faster previews on submission. The arXiv HTML Papers project remains experimental, but is gradually maturing as we better understand the needs of arXiv's readers and the technical opportunities presented by new standards and by advances in programming languages and AI.

Related papers

• Code as Representation: A Compilable Parsing Paradigm for Academic Documents [50.40789738182074]
  Compilable Academic Document Parsing (CADP) is a paradigm that reconstructs a full page as contextual La plus executable Python.<n>We introduce CADP-Bench, an expert-verified benchmark of full academic pages containing text and multiple SAE types.<n>Results show that even frontier models still struggle to produce high-fidelity executable reconstructions.
  arXiv  Detail & Related papers  (2026-08-18T09:10:43Z)
• AI-Friendly LaTeX: Using LaTeX Code as a Knowledge Source for Retrieval-Augmented Generation [0.0]
  Large language models can answer questions about textbooks, lecture notes, and programming exercises more reliably when their answers are grounded in an explicit knowledge source.<n>For mathematical and technical material, the original source can be a better starting point than a PDF, because it contains structural information, labels, sectioning commands, macros, and authorial intent that are often lost or distorted in PDF extraction.<n>This article describes a focused preprocessing approach for turning source, together with its compiled auxiliary files and optional author annotations, into chunks suitable for indexing in a vector database.
  arXiv  Detail & Related papers  (2026-05-21T18:01:51Z)
• Hidden Secrets in the arXiv: Discovering, Analyzing, and Preventing Unintentional Information Disclosure in Source Files of Scientific Preprints [4.620974866012306]
  We analyze 2.7M arXiv submissions with available source files across three dimensions of source file-induced information disclosure.<n>Our analysis reveals that nearly every arXiv submission contains some form of "hidden" information.<n>We provide ALC-NG to comprehensively remove files, metadata, and comments that are not needed to compile a paper.
  arXiv  Detail & Related papers  (2026-04-22T08:18:10Z)
• Paper2Web: Let's Make Your Paper Alive! [51.75896846964824]
  We introduce Paper2Web, a benchmark dataset and framework for assessing academic webpage generation.<n>We present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages.
  arXiv  Detail & Related papers  (2025-10-17T17:35:58Z)
• LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination [46.53643691093418]
  We introduce MTTrans, a collaborative multi-agent system designed to translate structured-formatted documents.<n>Trans ensures format preservation, structural fidelity, and consistency through six specialized agents.
  arXiv  Detail & Related papers  (2025-08-26T08:17:26Z)
• $A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement [53.14935624161711]
  Vision-language models (VLMs) have achieved remarkable progress across a range of visual understanding tasks.<n>We propose $A2R2$: Advancing Img2La Conversion via Visual Reasoning with Attention-Guided Refinement.<n>For effective evaluation, we introduce a new dataset, Img2LaTex-Hard-1K, consisting of 1,100 carefully curated and challenging examples.
  arXiv  Detail & Related papers  (2025-07-28T14:41:57Z)
• TeXBLEU: Automatic Metric for Evaluate LaTeX Format [4.337656290539519]
  We propose BLEU, a metric for evaluating mathematical expressions in the format built on the n-gram-based BLEU metric. The proposed BLEU consists of a tokenizer trained on the arXiv paper dataset and a fine-tuned embedding model with positional encoding.
  arXiv  Detail & Related papers  (2024-09-10T16:54:32Z)
• MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into $LaTeX$ Formulas for Improved Readability [10.757551947236879]
  We introduce MathBridge, the first extensive dataset for translating mathematical spoken sentences into formulas. MathBridge significantly enhances the capabilities of pretrained language models for converting to formulas from mathematical spoken sentences.
  arXiv  Detail & Related papers  (2024-08-07T18:07:15Z)
• MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition [2.325171167252542]
  We present an improved version of the benchmark dataset im2latex-100k, featuring 30 fonts instead of one. Second, we introduce the real-world dataset realFormula, with MEs extracted from papers. Third, we developed a MER model, MathNet, based on a convolutional vision transformer, with superior results on all four test sets.
  arXiv  Detail & Related papers  (2024-04-21T14:03:34Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text [32.15651290548974]
  We introduce OpenWebMath, an open dataset inspired by works containing 14.7B tokens of webpages from Common Crawl. We run small-scale experiments by training 1.4B parameter language models on OpenWebMath, showing that models trained on 14.7B tokens of our dataset surpass the performance of models trained on over 20x the amount of general language data.
  arXiv  Detail & Related papers  (2023-10-10T16:57:28Z)
• The Semantic Scholar Open Data Platform [92.2948743167744]
  Semantic Scholar (S2) is an open data platform and website aimed at accelerating science by helping scholars discover and understand scientific literature.<n>We combine public and proprietary data sources using state-of-the-art techniques for scholarly PDF content extraction and automatic knowledge graph construction.<n>The graph includes advanced semantic features such as structurally parsed text, natural language summaries, and vector embeddings.
  arXiv  Detail & Related papers  (2023-01-24T17:13:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.