# The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning

arXiv: https://arxiv.org/abs/2608.26602 · HTML: https://mlsanity.com/paper/2608.26602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025)
- [CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://mlsanity.com/paper/2408.03910/) (2024)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [RLCoder: Reinforcement Learning for Repository-Level Code Completion](https://mlsanity.com/paper/2407.19487/) (2024)
- [RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation](https://mlsanity.com/paper/2509.16198/) (2025)
- [Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP](https://mlsanity.com/paper/2603.27277/) (2026)
- [RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation](https://mlsanity.com/paper/2507.14791/) (2025)
- [GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion](https://mlsanity.com/paper/2509.05980/) (2025)
- [Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants](https://mlsanity.com/paper/2601.10112/) (2026)

## Abstract (arXiv)

Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements, and explicit relation graphs add ongoing maintenance burden. We propose an entity-only external interface with task-conditioned relation materialization during inference. A two-layer index separates global routing from local entity focus and is evaluated on DeepSeek-V4-Flash and SWE-bench Verified. The base, one-layer, and two-layer conditions achieve 92.1%, 94.2%, and 95.6% success, respectively, under zero pre-built entity-relation edges.