使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill audit-data-contamination开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
仓库原始内容
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
audit-data-contamination
Purpose
Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.
Input contract
yaml
required: [dataset_partitions, training_sources, evaluation_records]
optional: [release_history, deduplication_keys, access_logs]
constraints: [each contamination claim requires a matched record, pathway, and comparison basis]Procedure
- Define partition, temporal, entity, and disclosure boundaries.
- Match evaluation items against training and public-source records using declared keys.
- Test suspected leakage pathways and compare affected with unaffected cases.
- Classify confirmed, plausible, and unassessed contamination with impact notes.
Output contract
yaml
produces: [contamination_matches, pathway_map, affected_case_set, impact_assessment, audit_uncertainties]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]Quality gates
- Matching keys and time boundaries are recorded.
- False-positive matches are sampled and documented.
Failure and counterexamples
Do not call lexical overlap contamination without a disclosure pathway, and do not infer clean separation from missing metadata.
Provenance map
resolved: knowledge-acquisition-contamination-audit
