The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning
Year: 2026
Type: preprint
Abstract: 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.
Source: Figshare
Author: fei ding
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204474646
