研究项目组合审计框架
通过证据矩阵和审查卡审计研究项目组合,输出风险、纠正行动及验证方案。
完整提示词
Main objective: > Perform a rigorous, transparent workflow for Research Program Portfolio Audit that preserves research integrity, decision traceability and claims proportional to evidence. ## 1. CONTEXT Define research object, study/model/artifact, responsible people, data/code/materials, decision stage, relevant standards, risks and intended use. ## 2. DOMAIN STANDARD Research translation should separate evidence quality from values, feasibility, costs, equity and stakeholder priorities. Decision frameworks should make trade-offs visible rather than disguise them as scientific facts. ## 3. SPECIALIZED FOCUS For **Research Program Portfolio Audit**: - define the exact integrity/model/project question - identify source documents and evidence - separate mandatory requirements from good practice - identify hidden assumptions and incentives - test failure, misuse and edge cases - produce corrective actions with verification ## 4. INTEGRITY CHECKS - research priority is tied to a documented gap - project milestones depend on evidence, not calendar alone - risks and dependencies have owners - resources match critical path - stakeholder input is distinguished from empirical evidence - policy translation states uncertainty - impact metrics are defined prospectively - post-study review captures null/negative learning ## 5. REVIEW CARD ```text Issue: Source / evidence: Observed state: Expected standard: Assumption: Risk: Alternative explanation: Corrective action: Owner: Verification: Residual uncertainty: ``` ## 6. REQUIRED MATRICES ### Research Roadmap Matrix | Workstream | Question | Evidence needed | Owner | Dependency | Milestone | Decision gate | |---|---|---|---|---|---|---| ### Evidence-to-Decision Matrix | Option | Evidence | Uncertainty | Benefits | Harms/costs | Equity | Feasibility | Decision | |---|---|---|---|---|---|---|---| ## 7. ANTI-OVERCLAIM / ANTI-BLAME RULES Do not infer misconduct from anomaly alone, treat reporting compliance as proof of validity, select a model only by fit, hide failed replications, use stakeholder preference as evidence, or convert uncertain evidence into deterministic policy claims. ## 8. REQUIRED OUTPUT 1. Scope and evidence base. 2. Standard/method applied. 3. Key findings. 4. Required matrices. 5. Alternative explanations / models. 6. Robustness or verification plan. 7. Corrective / implementation actions. 8. Residual limitations. End with **Final Integrity Check** confirming traceability from evidence to recommendation or scientific claim. This supports scientific work and does not replace required formal ethical, institutional, regulatory or specialist procedures.
分类与标签
思维提升、研究审计、项目决策、证据评估、风险复盘