JQD:DM launches Special Workflow Issue with shared skill-file LLM gatekeeping in peer review
manoelribeiro · x · 2026-10-13
The Journal of Quantitative Description: Digital Media announced a Special Workflow Issue that bakes AI into every stage of publishing as an experiment to rebalance AI-heavy academic workflows.
Key design choices:
- AI use is allowed and assumed at all stages, but outputs must be verified by authors and actually good — the editors note one-shot LLM drafts are often bad enough to merit rejection, including at the LOI stage.
- Editors use LLMs only via a shared "skill" file: authors upload it to any model (local/open-weight or corporate) that then evaluates submissions; manuscripts must pass this gate with an attached LLM report before human review, with iteration allowed.
- Reviewers focus only on theoretical value, conceptual coherence, and contribution, hoping the pre-screening raises reviewer acceptance and speed.
Letters of Inquiry due Oct 25.
More from coding & agent
- PageIndex SDK v0.4 claims tree indexing now cheaper than vector indexing by ~15% — solyarisoftware · 2026-10-13
- Economist: agentic coding lets you write your own Fortran optimizers, not just ask for Stata packages — Apoorva__Lal · 2026-10-13
- Tencent open-sources Agent Memory: local long-term memory, 61% fewer tokens, 48%→76% accuracy — solyarisoftware · 2026-10-13
- Testing AI agents with simulations: replay real traces, 50 curated sims beat 1000 random ones — HamelHusain · 2026-10-13
- How humans and Copilot agents split the work to build a GitHub Copilot beginner course — DanWahlin · 2026-10-13
- Engineers distill their AGI debate into an essay on self-verifying, continuously improving agents — dotey · 2026-10-13