reproducibility

A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots. 9 bio_* tools + workbench UI + publication-grade figure skills.

Make your research agent hard to fool — the discipline layer for agentic research: breakthrough loop, hard-to-fool harness checklist, claim-polarity gates, engineering rules with their tuition

DeepSeek Harness tools for reproducing the ml-quant-trading protocol v1 benchmark.

Deterministic revision-pinned benchmarks and regression evidence for DeepSeek Harness

Evidence-first frontier AI radar and reproducibility gate for DeepSeek Harness

DSH 插件：Jupyter 式活体运行本——回合可回放的数据流 DAG，含 git 提交出处节点、子 agent 交接边、持久账本、悬停重跑与 LLM 解释

Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay, evidence bundles.

Reproducible paired A/B experiments for DeepSeek Harness plugins, with isolated runners, auditable evidence, and deterministic promotion gates.