dsh-frontier-math: Frontier Mathematical Research Workflows Using DeepSeek Harness
dsh-frontier-math is a frontier mathematics research plugin for DeepSeek Harness (DSH). Its core philosophy is to establish rigorous, structured processes that improve research quality rather than promise automatic problem solving. The plugin provides four core tools—project initiation, literature audit, conjecture recording, and certificate generation—enforcing high open-endedness and clarity in problem statements, and ensuring reliable outputs through multi-source retrieval, dependency graph maintenance, and independent verification. The article details its installation and configuration, typical workflows (including scoring, auditing, and verification), and applicable scenarios, while highlighting concurrency limits in data storage and blind spots in automated retrieval. It is suitable for developers and researchers.
Read Moredsh-rigorquant: DSH Session-level Research Plugin for Experimental/Computational Mathematics
dsh-rigorquant is an MIT-licensed plugin for DeepSeek Harness (DSH) designed to optimize long-term research workflows in experimental/computational mathematics through context-isolated multi-agent collaboration. It addresses the conflation of hypothesis generation, exploration, verification, and implementation by organizing a single session into a research laboratory with boundaries, division of labor, and pre-checks. Its core mechanisms include parallel exploration, independent re-derivation of analysis forms and bounds, elimination of invalid paths via counterexamples, and evidence verification by the meta-validator `rq_check.py`, which rejects passing conclusions lacking evidence. The plugin introduces a "Pre-Implementation Four-Check Battery" to ensure sufficient evidence exists before numerical implementation. For stochastic tasks, it employs fixed seeds and a Law of Large Numbers (LLN) convention, and offers an optional Jacobian MCP upgrade path.
Read More