Credentials

Press commentary, peer review, research data and standards work.

2
press citations
11
peer reviews with DOI
5
works with DOI
2
IETF drafts

Cited in the press

Expert commentary in the technology press.

2026-09-13·GENZ TECH

Going Offline Doesn't Remove Password Risk. It Swaps It.

Expert commentary: offline versus cloud password managers — which failure mode you choose

2026-09-11·TechRound

Anthropic Discloses Fourth Unauthorised Claude Access Incident: Is The Security Industry Prepared For AI Breaches?

Expert commentary: AI agents with legitimate access and enterprise threat models

Peer review

Open peer review for Qeios and PREreview, each review with its own DOI.

ORCID 0000-0002-9120-7298

Research and open data

Technical reports and the datasets behind them.

2026-09-11·Report · Zenodo

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

How often should an agent's context be cleared? 36 runs, six session-length policies, six replicates each, 4086 tests and zero failures. Cost is U-shaped in session length: clearing after every task costs 25.3% more than clearing every third, and never clearing costs 15.6% more. Exact permutation tests put both extremes outside the optimum (p = 0.0022 and p = 0.0108) while three, four and six tasks per session are indistinguishable - the optimum is a plateau, not a point. The U decomposes into cache writes falling and context-per-call rising, priced 12.5:1 against each other.

10.5281/zenodo.22699668 · PDF

2026-09-10·Report · Zenodo

The Context Economy of Agentic LLM Sessions: Where the Money Actually Goes

722 agent sessions, 150,902 model calls, 34.6 billion tokens. Context handling accounts for 83.5% of modeled cost and generation for 16.5%; 80% of the spend comes from 3.3% of sessions. Includes two log-deduplication traps that change the answer by a factor of two in either direction, and the de-identified dataset.

10.5281/zenodo.22688706 · PDF

2026·Dataset · Zenodo

AI Tools Radar: GitHub and Hugging Face projects selected by arsentev.ai (monthly)

490 open-source AI projects selected and reviewed by the arsentev.ai radar since June 2026, with daily GitHub and Hugging Face API snapshots of how they evolve after selection. A new version is released every month.

10.5281/zenodo.22730450

2026·Dataset · Hugging Face

Context U-curve: 36 coding-agent runs under six context-clearing policies

Run-level token counters, modeled cost, wall clock and test outcomes for every run behind the U-curve report. Counters only - no prompts, no model output, no paths.

10.57967/hf/10366

Standards

Internet-Drafts at the IETF.

2026-09-10·IETF Internet-Draft, rev 00

Agent Run Metrics: A JSON Interchange Format for Resource Accounting of AI Agent Runs

draft-arsentev-agent-run-metrics

2026-09-11·IETF Internet-Draft, rev 00

Discovery and Retrieval of Publisher-Curated Context Files for Large Language Models

draft-arsentev-llm-context-discovery

Open-source tools

contextburn — a context-accounting meter for coding agents, MIT licensed.

Group participation

Standards working groups on AI agents.

Researchpeer-reviewed papers and the author's identifiers. · Press · About