RResearcharAcademic radar for researchers

Feed Venues Groups Network Inbox Profile

Your academic radar

One personalized feed of papers, calls for papers, collaborators and datasets — plus research groups and paid-in-points study recruitment.

Create account Log in

Top venues

Browse all

Loading…

Clear Every Third Task: A Measured U-Curve in the Context Economy of Coding Agents · Researchar

Back to feed

Paperopenalex

Clear Every Third Task: A Measured U-Curve in the Context Economy of Coding Agents

Evgenii Arsentev · OSF Preprints (OSF Preprints) 2026 · 2026

DOI: 10.17605/osf.io/5qtwy

0citations

Adversarial Robustness in Machine LearningComputability, Logic, AI AlgorithmsData Stream Mining TechniquesCoding (social sciences)Computer scienceContext (archaeology)+2

OPOOSF Preprints (OSF Preprints)Repository

Download PDF Publisher

Citations by source

Synced 2026-09-15T02:30:59.011110Z

0OpenAlex · primary0Semantic Scholar0Crossref

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Abstract

Mirror of the report "Clear Every Third Task: A Measured U-Curve in the Context Economy of Coding Agents" (Evgenii Arsentev, 2026; DOI 10.5281/zenodo.22699668) with its dataset of 36 coding-agent runs under six context-clearing policies. Dataset also on Hugging Face (DOI 10.57967/hf/10366). Tool: github.com/arsentev-ai/contextburn. More: arsentev.ai/research

Discussion (0)

No comments yet — start the discussion below.