# Code as Representation: A Compilable Parsing Paradigm for Academic Documents

arXiv: https://arxiv.org/abs/2608.17550 · HTML: https://mlsanity.com/paper/2608.17550/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning](https://mlsanity.com/paper/2402.12185/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm](https://mlsanity.com/paper/2506.05218/) (2025)
- [OneChart: Purify the Chart Structural Extraction via One Auxiliary Token](https://mlsanity.com/paper/2404.09987/) (2024)
- [ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing](https://mlsanity.com/paper/2505.11935/) (2025)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables](https://mlsanity.com/paper/2105.06400/) (2021)
- [READoc: A Unified Benchmark for Realistic Document Structured Extraction](https://mlsanity.com/paper/2409.05137/) (2024)
- [Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models](https://mlsanity.com/paper/2509.17589/) (2025)
- [LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement](https://mlsanity.com/paper/2409.14201/) (2024)
- [Tables to LaTeX: structure and content extraction from scientific tables](https://mlsanity.com/paper/2210.17246/) (2022)
- [HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding](https://mlsanity.com/paper/2403.19723/) (2024)
- [Visual Programmability: A Guide for Code-as-Thought in Chart Understanding](https://mlsanity.com/paper/2509.09286/) (2025)
- [DREAM: Document Reconstruction via End-to-end Autoregressive Model](https://mlsanity.com/paper/2507.05805/) (2025)
- [ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference](https://mlsanity.com/paper/2509.03565/) (2025)

## Abstract (arXiv)

Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For Multimodal Large Language Models (MLLMs), the core challenge is not only perception, but representation: scientific pages interleave text with Structured Academic Elements (SAEs) such as tables, formulas, charts, and pseudocode, whose structure, data, and logic are poorly preserved by common surrogates like Markdown. We therefore propose Compilable Academic Document Parsing (CADP), a paradigm that reconstructs a full page as contextual LaTeX plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page. To support this setting, we introduce CADP-Bench, an expert-verified benchmark of full academic pages containing tightly coupled text and multiple SAE types, evaluated through a re-injection compilation protocol. We further study current capabilities using SOTA MLLMs and an exploratory multi-agent baseline that incorporates common agentic techniques. Results show that even frontier models still struggle to produce high-fidelity executable reconstructions, highlighting substantial room for improvement in structure-aware scientific document parsing. CADP-Bench is released for future research.