Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-29 · source-backed
arXiv 2607.25996 moves code reasoning from function level to repository level, with ground-truth call chains from dynamic tracing of real pytest runs and LLM-based I/O rewriting to suppress memorization. Call Chain Prediction shows high precision and low recall, and longer contexts don't consistently help because of added noise. Performance drops on rewritten data confirm partial memorization reliance.
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entity: LLM / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; overlapping topics (context, data).
Simon Willison released LLM / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (code, even).
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.
Simon Willison released LLM / Same source domain / Shared topic
Linked by a graph relationship (Simon Willison released LLM); reported by the same outlet (arxiv.org); overlapping topics (code, data).
LLM uses OpenAI / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-06-19.
LLM uses OpenAI / Shared topic / Tension
Linked by a graph relationship (LLM uses OpenAI); overlapping topics (level, reasoning); pushes against this story (vs).
Simon Willison released LLM / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-07-19.